rinatkurmaev / flux-dev-lora-tatra-t3

A lora model for making photos of Tatra t3 tram

Warm

Public
163 runs
H100

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2

Model

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e4

kh3hjqkss1rma0cmvmaav1nzew

Status

Succeeded

Source

Web

Hardware

H100

Total duration

9.4s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street in Florida. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-06T21:05:03.597897Z",
  "created_at": "2025-02-06T21:04:54.216000Z",
  "data_removed": false,
  "error": null,
  "id": "kh3hjqkss1rma0cmvmaav1nzew",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-06 21:04:54.243 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-06 21:04:54.245 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s\nfree=28540482613248\nDownloading weights\n2025-02-06T21:04:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxq5pbphd/weights url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar\n2025-02-06T21:05:00Z | INFO  | [ Complete ] dest=/tmp/tmpxq5pbphd/weights size=\"172 MB\" total_elapsed=5.808s url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar\nDownloaded weights in 5.84s\n2025-02-06 21:05:00.084 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/845a4e25b4cf9030\n2025-02-06 21:05:00.153 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 125/304 [00:00<00:00, 1233.37it/s]\nApplying LoRA:  82%|████████▏ | 249/304 [00:00<00:00, 982.48it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 974.10it/s]\n2025-02-06 21:05:00.466 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-06 21:05:00.466 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.38s\nrunning quantized prediction\nUsing seed: 3720543067\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.72it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 13.03it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.61it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.26it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.94it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.93it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.96it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.78it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.78it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.81it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.88it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.15it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 9.376099707,
    "total_time": 9.381897
  },
  "output": [
    "https://replicate.delivery/xezq/HgjdU3lEEL6bC1tbJKba0XP1JfjMatftkOm4kqetLaGffqlhC/out-0.png"
  ],
  "started_at": "2025-02-06T21:04:54.221797Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-23h76m2ufbucevfarwy2vscwcr6aifgody6bmlonqhsbjr7nyx3q",
    "get": "https://api.replicate.com/v1/predictions/kh3hjqkss1rma0cmvmaav1nzew",
    "cancel": "https://api.replicate.com/v1/predictions/kh3hjqkss1rma0cmvmaav1nzew/cancel"
  },
  "version": "bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2"
}

Generated in

9.4 seconds

Tweak it Share Report

2025-02-06 21:04:54.243 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-06 21:04:54.245 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s
free=28540482613248
Downloading weights
2025-02-06T21:04:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxq5pbphd/weights url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar
2025-02-06T21:05:00Z | INFO  | [ Complete ] dest=/tmp/tmpxq5pbphd/weights size="172 MB" total_elapsed=5.808s url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar
Downloaded weights in 5.84s
2025-02-06 21:05:00.084 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/845a4e25b4cf9030
2025-02-06 21:05:00.153 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████      | 125/304 [00:00<00:00, 1233.37it/s]
Applying LoRA:  82%|████████▏ | 249/304 [00:00<00:00, 982.48it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 974.10it/s]
2025-02-06 21:05:00.466 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-06 21:05:00.466 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.38s
running quantized prediction
Using seed: 3720543067
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.72it/s]
 14%|█▍        | 4/28 [00:00<00:01, 13.03it/s]
 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.61it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.26it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.94it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.93it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.96it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.78it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.78it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.81it/s]
100%|██████████| 28/28 [00:02<00:00, 10.88it/s]
100%|██████████| 28/28 [00:02<00:00, 11.15it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2

Model

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e4

kh3hjqkss1rma0cmvmaav1nzew

Status

Succeeded

Source

Web

Hardware

H100

Total duration

9.4s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street in Florida. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-06T21:05:03.597897Z",
  "created_at": "2025-02-06T21:04:54.216000Z",
  "data_removed": false,
  "error": null,
  "id": "kh3hjqkss1rma0cmvmaav1nzew",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street in Florida. A vintage photo. 60s",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-06 21:04:54.243 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-06 21:04:54.245 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s\nfree=28540482613248\nDownloading weights\n2025-02-06T21:04:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxq5pbphd/weights url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar\n2025-02-06T21:05:00Z | INFO  | [ Complete ] dest=/tmp/tmpxq5pbphd/weights size=\"172 MB\" total_elapsed=5.808s url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar\nDownloaded weights in 5.84s\n2025-02-06 21:05:00.084 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/845a4e25b4cf9030\n2025-02-06 21:05:00.153 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 125/304 [00:00<00:00, 1233.37it/s]\nApplying LoRA:  82%|████████▏ | 249/304 [00:00<00:00, 982.48it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 974.10it/s]\n2025-02-06 21:05:00.466 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-06 21:05:00.466 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.38s\nrunning quantized prediction\nUsing seed: 3720543067\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.72it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 13.03it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.61it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.26it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.94it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.93it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.96it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.78it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.78it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.81it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.88it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.15it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 9.376099707,
    "total_time": 9.381897
  },
  "output": [
    "https://replicate.delivery/xezq/HgjdU3lEEL6bC1tbJKba0XP1JfjMatftkOm4kqetLaGffqlhC/out-0.png"
  ],
  "started_at": "2025-02-06T21:04:54.221797Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-23h76m2ufbucevfarwy2vscwcr6aifgody6bmlonqhsbjr7nyx3q",
    "get": "https://api.replicate.com/v1/predictions/kh3hjqkss1rma0cmvmaav1nzew",
    "cancel": "https://api.replicate.com/v1/predictions/kh3hjqkss1rma0cmvmaav1nzew/cancel"
  },
  "version": "bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2"
}

Generated in

9.4 seconds

Tweak it Share Report

2025-02-06 21:04:54.243 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-06 21:04:54.245 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s
free=28540482613248
Downloading weights
2025-02-06T21:04:54Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxq5pbphd/weights url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar
2025-02-06T21:05:00Z | INFO  | [ Complete ] dest=/tmp/tmpxq5pbphd/weights size="172 MB" total_elapsed=5.808s url=https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar
Downloaded weights in 5.84s
2025-02-06 21:05:00.084 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/845a4e25b4cf9030
2025-02-06 21:05:00.153 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-06 21:05:00.153 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████      | 125/304 [00:00<00:00, 1233.37it/s]
Applying LoRA:  82%|████████▏ | 249/304 [00:00<00:00, 982.48it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 974.10it/s]
2025-02-06 21:05:00.466 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-06 21:05:00.466 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.38s
running quantized prediction
Using seed: 3720543067
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.72it/s]
 14%|█▍        | 4/28 [00:00<00:01, 13.03it/s]
 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.61it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.26it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.94it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.93it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.96it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.78it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.78it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.81it/s]
100%|██████████| 28/28 [00:02<00:00, 10.88it/s]
100%|██████████| 28/28 [00:02<00:00, 11.15it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2

Model

rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e4

mw99pe5rcxrma0cmvmfr5yhz40

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.2s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-06T21:17:14.303710Z",
  "created_at": "2025-02-06T21:17:11.143000Z",
  "data_removed": false,
  "error": null,
  "id": "mw99pe5rcxrma0cmvmfr5yhz40",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street in Florida, Miami. A vintage photo. 60s",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/fRIYLNzQKXw5QCXaef0fN2rZusVW2Rd9BBVU4Deg99hyKmlhC/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 1035370845\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.35it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.82it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.83it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.39it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.15it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.78it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.76it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.77it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.77it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.78it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.62it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.58it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.64it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.66it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.96it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.125534473,
    "total_time": 3.16071
  },
  "output": [
    "https://replicate.delivery/xezq/7CNp2VSrVuLXE9h2fwfaLoCy762Ai3fTCDjbrkRlmXP1GbZoA/out-0.png"
  ],
  "started_at": "2025-02-06T21:17:11.178176Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-3sdtuxu4eznxdsxodiwmoabz7cyb5xa52sgli4ue4x4jhl24xk5q",
    "get": "https://api.replicate.com/v1/predictions/mw99pe5rcxrma0cmvmfr5yhz40",
    "cancel": "https://api.replicate.com/v1/predictions/mw99pe5rcxrma0cmvmfr5yhz40/cancel"
  },
  "version": "bda1c7e46622f83ee865df8d269db866874bfccafd42b9d0292f7d80250051b2"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

kak13z0ar5rmc0cmwwpan28krc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.5s

Created

4 months ago

Input

mask
image
model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
  "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      image: "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street. A vintage photo. 60s",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
        "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-08T20:06:54.337767Z",
  "created_at": "2025-02-08T20:06:50.817000Z",
  "data_removed": false,
  "error": null,
  "id": "kak13z0ar5rmc0cmwwpan28krc",
  "input": {
    "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
    "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Loaded LoRAs in 0.56s\nUsing seed: 47188\nPrompt: A tram TATRAT3 running a street. A vintage photo. 60s\n[!] Resizing input image from 720x480 to 720x480\n[!] inpaint mode\n  0%|          | 0/23 [00:00<?, ?it/s]\n  4%|▍         | 1/23 [00:00<00:02,  7.93it/s]\n  9%|▊         | 2/23 [00:00<00:02,  8.46it/s]\n 13%|█▎        | 3/23 [00:00<00:02,  8.65it/s]\n 17%|█▋        | 4/23 [00:00<00:02,  8.74it/s]\n 22%|██▏       | 5/23 [00:00<00:02,  8.79it/s]\n 26%|██▌       | 6/23 [00:00<00:01,  8.81it/s]\n 30%|███       | 7/23 [00:00<00:01,  8.83it/s]\n 35%|███▍      | 8/23 [00:00<00:01,  8.85it/s]\n 39%|███▉      | 9/23 [00:01<00:01,  8.85it/s]\n 43%|████▎     | 10/23 [00:01<00:01,  8.85it/s]\n 48%|████▊     | 11/23 [00:01<00:01,  8.86it/s]\n 52%|█████▏    | 12/23 [00:01<00:01,  8.86it/s]\n 57%|█████▋    | 13/23 [00:01<00:01,  8.86it/s]\n 61%|██████    | 14/23 [00:01<00:01,  8.86it/s]\n 65%|██████▌   | 15/23 [00:01<00:00,  8.86it/s]\n 70%|██████▉   | 16/23 [00:01<00:00,  8.86it/s]\n 74%|███████▍  | 17/23 [00:01<00:00,  8.87it/s]\n 78%|███████▊  | 18/23 [00:02<00:00,  8.86it/s]\n 83%|████████▎ | 19/23 [00:02<00:00,  8.86it/s]\n 87%|████████▋ | 20/23 [00:02<00:00,  8.87it/s]\n 91%|█████████▏| 21/23 [00:02<00:00,  8.87it/s]\n 96%|█████████▌| 22/23 [00:02<00:00,  8.87it/s]\n100%|██████████| 23/23 [00:02<00:00,  8.89it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.491512022,
    "total_time": 3.520767
  },
  "output": [
    "https://replicate.delivery/xezq/wQ99OQfR9TQ1GqXH9aTgJykB9SyIvrdY9gtgucXNo1RvWrGKA/out-0.png"
  ],
  "started_at": "2025-02-08T20:06:50.846255Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-sdsjfbzpskbo5qzc7gn33kkfvsnkbdkig25y42blaa6reyaedcmq",
    "get": "https://api.replicate.com/v1/predictions/kak13z0ar5rmc0cmwwpan28krc",
    "cancel": "https://api.replicate.com/v1/predictions/kak13z0ar5rmc0cmwwpan28krc/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.5 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

3j3qjzc8dhrm80cmwwxrtymh6r

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.6s

Created

4 months ago

Input

mask
image
model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
  "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      image: "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street. A vintage photo. 60s",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
        "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-08T20:23:49.638139Z",
  "created_at": "2025-02-08T20:23:46.028000Z",
  "data_removed": false,
  "error": null,
  "id": "3j3qjzc8dhrm80cmwwxrtymh6r",
  "input": {
    "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
    "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Loaded LoRAs in 0.56s\nUsing seed: 62631\nPrompt: A tram TATRAT3 running a street. A vintage photo. 60s\n[!] Resizing input image from 720x480 to 720x480\n[!] inpaint mode\n  0%|          | 0/23 [00:00<?, ?it/s]\n  4%|▍         | 1/23 [00:00<00:02,  7.94it/s]\n  9%|▊         | 2/23 [00:00<00:02,  8.48it/s]\n 13%|█▎        | 3/23 [00:00<00:02,  8.66it/s]\n 17%|█▋        | 4/23 [00:00<00:02,  8.75it/s]\n 22%|██▏       | 5/23 [00:00<00:02,  8.80it/s]\n 26%|██▌       | 6/23 [00:00<00:01,  8.84it/s]\n 30%|███       | 7/23 [00:00<00:01,  8.86it/s]\n 35%|███▍      | 8/23 [00:00<00:01,  8.88it/s]\n 39%|███▉      | 9/23 [00:01<00:01,  8.89it/s]\n 43%|████▎     | 10/23 [00:01<00:01,  8.90it/s]\n 48%|████▊     | 11/23 [00:01<00:01,  8.90it/s]\n 52%|█████▏    | 12/23 [00:01<00:01,  8.90it/s]\n 57%|█████▋    | 13/23 [00:01<00:01,  8.90it/s]\n 61%|██████    | 14/23 [00:01<00:01,  8.91it/s]\n 65%|██████▌   | 15/23 [00:01<00:00,  8.91it/s]\n 70%|██████▉   | 16/23 [00:01<00:00,  8.91it/s]\n 74%|███████▍  | 17/23 [00:01<00:00,  8.90it/s]\n 78%|███████▊  | 18/23 [00:02<00:00,  8.90it/s]\n 83%|████████▎ | 19/23 [00:02<00:00,  8.91it/s]\n 87%|████████▋ | 20/23 [00:02<00:00,  8.90it/s]\n 91%|█████████▏| 21/23 [00:02<00:00,  8.91it/s]\n 96%|█████████▌| 22/23 [00:02<00:00,  8.91it/s]\n100%|██████████| 23/23 [00:02<00:00,  8.93it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.490073311,
    "total_time": 3.610139
  },
  "output": [
    "https://replicate.delivery/xezq/p5p0gdUry1ZRH1COZs7jre58KfNxfp8jS3iSzS2EyTHr6taoA/out-0.png"
  ],
  "started_at": "2025-02-08T20:23:46.148065Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-iz3emp4rtzh5ggmmziykvd2jm2cqq57zvfcpw32ttaqr6diaftxa",
    "get": "https://api.replicate.com/v1/predictions/3j3qjzc8dhrm80cmwwxrtymh6r",
    "cancel": "https://api.replicate.com/v1/predictions/3j3qjzc8dhrm80cmwwxrtymh6r/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.5 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

be7cm0m62hrmc0cmw9wajef080

Status

Succeeded

Source

Web

Hardware

H100

Total duration

4.9s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:12:21.956565Z",
  "created_at": "2025-02-07T22:12:17.044000Z",
  "data_removed": false,
  "error": null,
  "id": "be7cm0m62hrmc0cmw9wajef080",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:12:17.097 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:12:17.099 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=28858181668864\nDownloading weights\n2025-02-07T22:12:17Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpravyvxrk/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:12:18Z | INFO  | [ Complete ] dest=/tmp/tmpravyvxrk/weights size=\"215 MB\" total_elapsed=1.341s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 1.37s\n2025-02-07 22:12:18.468 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:12:18.548 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:12:18.548 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:12:18.548 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 124/304 [00:00<00:00, 1228.68it/s]\nApplying LoRA:  81%|████████▏ | 247/304 [00:00<00:00, 971.07it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 966.56it/s]\n2025-02-07 22:12:18.863 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:12:18.863 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 1681562567\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.54it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.95it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.93it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.52it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.21it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.89it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.86it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.86it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.87it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.85it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.70it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.71it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.75it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.79it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.07it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 4.880900741,
    "total_time": 4.912565
  },
  "output": [
    "https://replicate.delivery/xezq/3otQzUKepu1URa4Y6mfpT7Q94uxwIcA6crceSt9Rg3vL6GaoA/out-0.png"
  ],
  "started_at": "2025-02-07T22:12:17.075664Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-fkekpce4jfjhfaqspkh4oywqqij3p6hisjbucjh4s254smkszgoa",
    "get": "https://api.replicate.com/v1/predictions/be7cm0m62hrmc0cmw9wajef080",
    "cancel": "https://api.replicate.com/v1/predictions/be7cm0m62hrmc0cmw9wajef080/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

4.9 seconds

Tweak it Share Report

2025-02-07 22:12:17.097 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:12:17.099 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=28858181668864
Downloading weights
2025-02-07T22:12:17Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpravyvxrk/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:12:18Z | INFO  | [ Complete ] dest=/tmp/tmpravyvxrk/weights size="215 MB" total_elapsed=1.341s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 1.37s
2025-02-07 22:12:18.468 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:12:18.548 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:12:18.548 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:12:18.548 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████      | 124/304 [00:00<00:00, 1228.68it/s]
Applying LoRA:  81%|████████▏ | 247/304 [00:00<00:00, 971.07it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 966.56it/s]
2025-02-07 22:12:18.863 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:12:18.863 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 1681562567
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.54it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.95it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.93it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.52it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.21it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.89it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.86it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.86it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.87it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.85it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.70it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.71it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.75it/s]
100%|██████████| 28/28 [00:02<00:00, 10.79it/s]
100%|██████████| 28/28 [00:02<00:00, 11.07it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

t6r9mhz6tdrme0cmw9wbnf5xmr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

7.1s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:12:48.904581Z",
  "created_at": "2025-02-07T22:12:41.811000Z",
  "data_removed": false,
  "error": null,
  "id": "t6r9mhz6tdrme0cmw9wbnf5xmr",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running visible from front right on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:12:42.260 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:12:42.261 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=29142539214848\nDownloading weights\n2025-02-07T22:12:42Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuij78so6/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:12:45Z | INFO  | [ Complete ] dest=/tmp/tmpuij78so6/weights size=\"215 MB\" total_elapsed=3.066s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 3.09s\n2025-02-07 22:12:45.356 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:12:45.499 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:12:45.499 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:12:45.499 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  40%|████      | 123/304 [00:00<00:00, 1222.61it/s]\nApplying LoRA:  81%|████████  | 246/304 [00:00<00:00, 968.70it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 977.04it/s]\n2025-02-07 22:12:45.811 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:12:45.811 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.45s\nrunning quantized prediction\nUsing seed: 918440467\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.49it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.96it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.60it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.27it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.92it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.91it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.92it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.93it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.91it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.77it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.75it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.77it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.81it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.12it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.666143294,
    "total_time": 7.093581
  },
  "output": [
    "https://replicate.delivery/xezq/9nOvkD18oV7dF9QHTBTYoDJHLcvpd4NXVyVGgqTe0uMwuhGKA/out-0.png"
  ],
  "started_at": "2025-02-07T22:12:42.238438Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-hkuw4wiuta3r7utieteqt4mlgad25qvdrlo2tnmlmio5aa2zazpa",
    "get": "https://api.replicate.com/v1/predictions/t6r9mhz6tdrme0cmw9wbnf5xmr",
    "cancel": "https://api.replicate.com/v1/predictions/t6r9mhz6tdrme0cmw9wbnf5xmr/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

6.7 seconds

Tweak it Share Report

2025-02-07 22:12:42.260 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:12:42.261 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=29142539214848
Downloading weights
2025-02-07T22:12:42Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpuij78so6/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:12:45Z | INFO  | [ Complete ] dest=/tmp/tmpuij78so6/weights size="215 MB" total_elapsed=3.066s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 3.09s
2025-02-07 22:12:45.356 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:12:45.499 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:12:45.499 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:12:45.499 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  40%|████      | 123/304 [00:00<00:00, 1222.61it/s]
Applying LoRA:  81%|████████  | 246/304 [00:00<00:00, 968.70it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 977.04it/s]
2025-02-07 22:12:45.811 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:12:45.811 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.45s
running quantized prediction
Using seed: 918440467
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.49it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.96it/s]
 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.60it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.27it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.92it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.91it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.92it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.93it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.91it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.77it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.75it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.77it/s]
100%|██████████| 28/28 [00:02<00:00, 10.81it/s]
100%|██████████| 28/28 [00:02<00:00, 11.12it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

wtzr93sfpsrmc0cmw9xbjfsy70

Status

Succeeded

Source

Web

Hardware

H100

Total duration

5.7s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:14:11.732849Z",
  "created_at": "2025-02-07T22:14:06.006000Z",
  "data_removed": false,
  "error": null,
  "id": "wtzr93sfpsrmc0cmw9xbjfsy70",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running visible from front on a busy city street on a seafront. A cruise ship docker to a pier on a background ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:14:06.102 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:14:06.104 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=29125187952640\nDownloading weights\n2025-02-07T22:14:06Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpcz2y_kc5/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:14:08Z | INFO  | [ Complete ] dest=/tmp/tmpcz2y_kc5/weights size=\"215 MB\" total_elapsed=2.113s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 2.14s\n2025-02-07 22:14:08.242 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:14:08.318 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:14:08.318 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:14:08.318 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  39%|███▉      | 120/304 [00:00<00:00, 1176.59it/s]\nApplying LoRA:  78%|███████▊  | 238/304 [00:00<00:00, 962.53it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 964.65it/s]\n2025-02-07 22:14:08.634 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:14:08.634 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s\nrunning quantized prediction\nUsing seed: 1029488391\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 16.97it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.74it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.77it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.37it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.11it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.81it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.79it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.78it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.78it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.76it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.66it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.64it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.68it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.71it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.98it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 5.652079976,
    "total_time": 5.726849
  },
  "output": [
    "https://replicate.delivery/xezq/srADQ7YJf8QDYSS1fgxTmtShsXztIKAkTB8LNEtSWLgzeGaoA/out-0.png"
  ],
  "started_at": "2025-02-07T22:14:06.080769Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-kmwoig2v4akswbv2td3kopgi5z3shh6dvdlerxjbbijrmscl557a",
    "get": "https://api.replicate.com/v1/predictions/wtzr93sfpsrmc0cmw9xbjfsy70",
    "cancel": "https://api.replicate.com/v1/predictions/wtzr93sfpsrmc0cmw9xbjfsy70/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

5.7 seconds

Tweak it Share Report

2025-02-07 22:14:06.102 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:14:06.104 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=29125187952640
Downloading weights
2025-02-07T22:14:06Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpcz2y_kc5/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:14:08Z | INFO  | [ Complete ] dest=/tmp/tmpcz2y_kc5/weights size="215 MB" total_elapsed=2.113s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 2.14s
2025-02-07 22:14:08.242 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:14:08.318 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:14:08.318 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:14:08.318 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  39%|███▉      | 120/304 [00:00<00:00, 1176.59it/s]
Applying LoRA:  78%|███████▊  | 238/304 [00:00<00:00, 962.53it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 964.65it/s]
2025-02-07 22:14:08.634 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:14:08.634 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s
running quantized prediction
Using seed: 1029488391
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 16.97it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.74it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.77it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.37it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.11it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.81it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.79it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.78it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.78it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.76it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.66it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.64it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.68it/s]
100%|██████████| 28/28 [00:02<00:00, 10.71it/s]
100%|██████████| 28/28 [00:02<00:00, 10.98it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

qwj6y50zrsrme0cmwa1t02bdc4

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.1s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and red. The snowy mountains are on the background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\\nThe snowy mountains are on the background",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:23:57.813679Z",
  "created_at": "2025-02-07T22:23:51.750000Z",
  "data_removed": false,
  "error": null,
  "id": "qwj6y50zrsrme0cmwa1t02bdc4",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:23:51.796 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:23:51.797 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s\nfree=29389792985088\nDownloading weights\n2025-02-07T22:23:51Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmph51s9hmt/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:23:54Z | INFO  | [ Complete ] dest=/tmp/tmph51s9hmt/weights size=\"215 MB\" total_elapsed=2.558s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 2.58s\n2025-02-07 22:23:54.382 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:23:54.459 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:23:54.459 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:23:54.459 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  39%|███▉      | 120/304 [00:00<00:00, 1188.43it/s]\nApplying LoRA:  79%|███████▊  | 239/304 [00:00<00:00, 986.20it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 953.69it/s]\n2025-02-07 22:23:54.778 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:23:54.779 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 213122787\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.93it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 13.01it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.98it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.56it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.29it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.97it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.95it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.94it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.81it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.80it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.85it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.87it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.15it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.039796138,
    "total_time": 6.063679
  },
  "output": [
    "https://replicate.delivery/xezq/1O1evWKSBoTiWaftq0S81NhHwvNLY8mbeRAxGvJEJSP7PHaoA/out-0.png"
  ],
  "started_at": "2025-02-07T22:23:51.773883Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-qh2skpg7reg7gcghgfro2asbezfrpziremvzdpxc62tnptxyz4xa",
    "get": "https://api.replicate.com/v1/predictions/qwj6y50zrsrme0cmwa1t02bdc4",
    "cancel": "https://api.replicate.com/v1/predictions/qwj6y50zrsrme0cmwa1t02bdc4/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

6.0 seconds

Tweak it Share Report

2025-02-07 22:23:51.796 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:23:51.797 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s
free=29389792985088
Downloading weights
2025-02-07T22:23:51Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmph51s9hmt/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:23:54Z | INFO  | [ Complete ] dest=/tmp/tmph51s9hmt/weights size="215 MB" total_elapsed=2.558s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 2.58s
2025-02-07 22:23:54.382 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:23:54.459 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:23:54.459 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:23:54.459 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  39%|███▉      | 120/304 [00:00<00:00, 1188.43it/s]
Applying LoRA:  79%|███████▊  | 239/304 [00:00<00:00, 986.20it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 953.69it/s]
2025-02-07 22:23:54.778 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:23:54.779 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 213122787
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.93it/s]
 14%|█▍        | 4/28 [00:00<00:01, 13.01it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.98it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.56it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.29it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.97it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.95it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.95it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.94it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.92it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.81it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.80it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.85it/s]
100%|██████████| 28/28 [00:02<00:00, 10.87it/s]
100%|██████████| 28/28 [00:02<00:00, 11.15it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

vnxqg6hxnhrmc0cmwa3bdqece4

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.1s

Created

4 months ago

Input

seed: 256
model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and red. The snowy mountains are on the background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "seed": 256,
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      seed: 256,
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "seed": 256,
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "seed": 256,
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\\nThe snowy mountains are on the background",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:27:19.095290Z",
  "created_at": "2025-02-07T22:27:16.012000Z",
  "data_removed": false,
  "error": null,
  "id": "vnxqg6hxnhrmc0cmwa3bdqece4",
  "input": {
    "seed": 256,
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 256\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.65it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.96it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.93it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.49it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.23it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.81it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.80it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.83it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.84it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.81it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.64it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.65it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.71it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.72it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.03it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.072471561,
    "total_time": 3.08329
  },
  "output": [
    "https://replicate.delivery/xezq/FnBlPW6KWUrhCZ6YUE2xcXZRkvXy7nT80ffbCVaxoq7HrDNUA/out-0.png"
  ],
  "started_at": "2025-02-07T22:27:16.022818Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-my4olxqhoqtuoaoyz6dtc4jptdjzx7ezuxpwanvcdqqgtwtyta2q",
    "get": "https://api.replicate.com/v1/predictions/vnxqg6hxnhrmc0cmwa3bdqece4",
    "cancel": "https://api.replicate.com/v1/predictions/vnxqg6hxnhrmc0cmwa3bdqece4/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

ng0q524b89rm80cmwa397n1sdm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.6s

Created

4 months ago

Input

seed: 256
model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 on a city street. The tram is green and red. The snowy mountains are on the background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "seed": 256,
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      seed: 256,
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "seed": 256,
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "seed": 256,
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\\nThe snowy mountains are on the background",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:27:42.481446Z",
  "created_at": "2025-02-07T22:27:35.874000Z",
  "data_removed": false,
  "error": null,
  "id": "ng0q524b89rm80cmwa397n1sdm",
  "input": {
    "seed": 256,
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:27:35.906 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:27:35.907 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=28471593234432\nDownloading weights\n2025-02-07T22:27:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpv57dbkor/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:27:38Z | INFO  | [ Complete ] dest=/tmp/tmpv57dbkor/weights size=\"215 MB\" total_elapsed=3.046s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 3.07s\n2025-02-07 22:27:38.981 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:27:39.060 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:27:39.060 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:27:39.061 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  39%|███▉      | 118/304 [00:00<00:00, 1177.22it/s]\nApplying LoRA:  78%|███████▊  | 236/304 [00:00<00:00, 981.72it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 961.15it/s]\n2025-02-07 22:27:39.377 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:27:39.377 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 256\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.58it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.77it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.74it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.30it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 10.98it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.70it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.68it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.69it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.66it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.61it/s]\n 79%|███████▊  | 22/28 [00:02<00:00, 10.51it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.52it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.58it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.60it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.88it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.596790403,
    "total_time": 6.607446
  },
  "output": [
    "https://replicate.delivery/xezq/fMpYkC7rRoyGJKQ7LeoEpXIdewfbpZXI6evntmR28HpxbdohC/out-0.png"
  ],
  "started_at": "2025-02-07T22:27:35.884656Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-j6uvwyb5hw75c2je6apotpamhhjt5mpg3wbaw2ztvkvuqixgloca",
    "get": "https://api.replicate.com/v1/predictions/ng0q524b89rm80cmwa397n1sdm",
    "cancel": "https://api.replicate.com/v1/predictions/ng0q524b89rm80cmwa397n1sdm/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

6.6 seconds

Tweak it Share Report

2025-02-07 22:27:35.906 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:27:35.907 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=28471593234432
Downloading weights
2025-02-07T22:27:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpv57dbkor/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:27:38Z | INFO  | [ Complete ] dest=/tmp/tmpv57dbkor/weights size="215 MB" total_elapsed=3.046s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 3.07s
2025-02-07 22:27:38.981 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:27:39.060 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:27:39.060 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:27:39.061 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  39%|███▉      | 118/304 [00:00<00:00, 1177.22it/s]
Applying LoRA:  78%|███████▊  | 236/304 [00:00<00:00, 981.72it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 961.15it/s]
2025-02-07 22:27:39.377 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:27:39.377 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 256
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.58it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.77it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.74it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.30it/s]
 36%|███▌      | 10/28 [00:00<00:01, 10.98it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.70it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.68it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.69it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.66it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.61it/s]
 79%|███████▊  | 22/28 [00:02<00:00, 10.51it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.52it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.58it/s]
100%|██████████| 28/28 [00:02<00:00, 10.60it/s]
100%|██████████| 28/28 [00:02<00:00, 10.88it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

e7vkvgp6q9rme0cmwa4bach08g

Status

Succeeded

Source

Web

Hardware

H100

Total duration

5.9s

Created

4 months ago

Input

seed: 512
model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and red. The snowy mountains are on the background
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "seed": 512,
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      seed: 512,
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "seed": 512,
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "seed": 512,
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\\nThe snowy mountains are on the background",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:30:08.093380Z",
  "created_at": "2025-02-07T22:30:02.170000Z",
  "data_removed": false,
  "error": null,
  "id": "e7vkvgp6q9rme0cmwa4bach08g",
  "input": {
    "seed": 512,
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 22:30:02.686 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 22:30:02.687 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s\nfree=28905335238656\nDownloading weights\n2025-02-07T22:30:02Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpcg_7_kbx/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T22:30:04Z | INFO  | [ Complete ] dest=/tmp/tmpcg_7_kbx/weights size=\"215 MB\" total_elapsed=1.868s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 1.90s\n2025-02-07 22:30:04.584 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 22:30:04.666 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 22:30:04.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 22:30:04.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  40%|████      | 122/304 [00:00<00:00, 1206.48it/s]\nApplying LoRA:  80%|███████▉  | 243/304 [00:00<00:00, 973.12it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 958.04it/s]\n2025-02-07 22:30:04.984 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 22:30:04.984 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 512\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 16.84it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.70it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.75it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.37it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.05it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.72it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.72it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.76it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.77it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.71it/s]\n 79%|███████▊  | 22/28 [00:02<00:00, 10.56it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.59it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.62it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.68it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.93it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 5.429609817,
    "total_time": 5.92338
  },
  "output": [
    "https://replicate.delivery/xezq/f8BJD10PgmT5J6hA0rjUw7pM1yUQp8KjMfrPtEo9y8hwtDNUA/out-0.png"
  ],
  "started_at": "2025-02-07T22:30:02.663770Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-uyyavcn5xtqaodq5m7yllluqngguzuaya2rr52hytwzzvpdopmuq",
    "get": "https://api.replicate.com/v1/predictions/e7vkvgp6q9rme0cmwa4bach08g",
    "cancel": "https://api.replicate.com/v1/predictions/e7vkvgp6q9rme0cmwa4bach08g/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

5.4 seconds

Tweak it Share Report

2025-02-07 22:30:02.686 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 22:30:02.687 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s
free=28905335238656
Downloading weights
2025-02-07T22:30:02Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpcg_7_kbx/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T22:30:04Z | INFO  | [ Complete ] dest=/tmp/tmpcg_7_kbx/weights size="215 MB" total_elapsed=1.868s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 1.90s
2025-02-07 22:30:04.584 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 22:30:04.666 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 22:30:04.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 22:30:04.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  40%|████      | 122/304 [00:00<00:00, 1206.48it/s]
Applying LoRA:  80%|███████▉  | 243/304 [00:00<00:00, 973.12it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 958.04it/s]
2025-02-07 22:30:04.984 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 22:30:04.984 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 512
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 16.84it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.70it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.75it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.37it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.05it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.72it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.72it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.76it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.77it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.71it/s]
 79%|███████▊  | 22/28 [00:02<00:00, 10.56it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.59it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.62it/s]
100%|██████████| 28/28 [00:02<00:00, 10.68it/s]
100%|██████████| 28/28 [00:02<00:00, 10.93it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

rd2nkeqnq1rme0cmwa98g0faem

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.2s

Created

4 months ago

Input

seed: 1024
model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "seed": 1024,
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      seed: 1024,
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "seed": 1024,
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "seed": 1024,
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:41:17.704466Z",
  "created_at": "2025-02-07T22:41:09.560000Z",
  "data_removed": false,
  "error": null,
  "id": "rd2nkeqnq1rme0cmwa98g0faem",
  "input": {
    "seed": 1024,
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Loaded LoRAs in 0.58s\nUsing seed: 1024\nPrompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.\n[!] txt2img mode\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:06,  3.99it/s]\n  7%|▋         | 2/28 [00:00<00:05,  4.50it/s]\n 11%|█         | 3/28 [00:00<00:05,  4.25it/s]\n 14%|█▍        | 4/28 [00:00<00:05,  4.14it/s]\n 18%|█▊        | 5/28 [00:01<00:05,  4.08it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  4.05it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  4.02it/s]\n 29%|██▊       | 8/28 [00:01<00:04,  4.01it/s]\n 32%|███▏      | 9/28 [00:02<00:04,  4.00it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  4.00it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  4.00it/s]\n 43%|████▎     | 12/28 [00:02<00:04,  3.99it/s]\n 46%|████▋     | 13/28 [00:03<00:03,  3.99it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.99it/s]\n 54%|█████▎    | 15/28 [00:03<00:03,  3.99it/s]\n 57%|█████▋    | 16/28 [00:03<00:03,  3.99it/s]\n 61%|██████    | 17/28 [00:04<00:02,  3.98it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.98it/s]\n 68%|██████▊   | 19/28 [00:04<00:02,  3.99it/s]\n 71%|███████▏  | 20/28 [00:04<00:02,  3.99it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.99it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.98it/s]\n 82%|████████▏ | 23/28 [00:05<00:01,  3.98it/s]\n 86%|████████▌ | 24/28 [00:05<00:01,  3.99it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.98it/s]\n 93%|█████████▎| 26/28 [00:06<00:00,  3.98it/s]\n 96%|█████████▋| 27/28 [00:06<00:00,  3.98it/s]\n100%|██████████| 28/28 [00:06<00:00,  3.98it/s]\n100%|██████████| 28/28 [00:06<00:00,  4.01it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.061713238,
    "total_time": 8.144466
  },
  "output": [
    "https://replicate.delivery/xezq/O77IAK4T7eTdd6zApQVbky8FPlOk6WB36IuOvvFVtDgG8hGKA/out-0.png"
  ],
  "started_at": "2025-02-07T22:41:09.642753Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-dvkb4bt5s4325qsevixwithnkthcyenn6cdabzsaoo2gwis4pwrq",
    "get": "https://api.replicate.com/v1/predictions/rd2nkeqnq1rme0cmwa98g0faem",
    "cancel": "https://api.replicate.com/v1/predictions/rd2nkeqnq1rme0cmwa98g0faem/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

8.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

th9j23hkt5rmc0cmwaat95a71w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

8.1s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:43:44.592121Z",
  "created_at": "2025-02-07T22:43:36.529000Z",
  "data_removed": false,
  "error": null,
  "id": "th9j23hkt5rmc0cmwaat95a71w",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Loaded LoRAs in 0.57s\nUsing seed: 45568\nPrompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green. The tram visible from front right side.\n[!] txt2img mode\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:06,  3.98it/s]\n  7%|▋         | 2/28 [00:00<00:05,  4.49it/s]\n 11%|█         | 3/28 [00:00<00:05,  4.24it/s]\n 14%|█▍        | 4/28 [00:00<00:05,  4.14it/s]\n 18%|█▊        | 5/28 [00:01<00:05,  4.09it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  4.05it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  4.03it/s]\n 29%|██▊       | 8/28 [00:01<00:04,  4.02it/s]\n 32%|███▏      | 9/28 [00:02<00:04,  4.01it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  4.00it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  4.00it/s]\n 43%|████▎     | 12/28 [00:02<00:04,  3.99it/s]\n 46%|████▋     | 13/28 [00:03<00:03,  3.99it/s]\n 50%|█████     | 14/28 [00:03<00:03,  3.99it/s]\n 54%|█████▎    | 15/28 [00:03<00:03,  3.99it/s]\n 57%|█████▋    | 16/28 [00:03<00:03,  3.99it/s]\n 61%|██████    | 17/28 [00:04<00:02,  3.99it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  3.99it/s]\n 68%|██████▊   | 19/28 [00:04<00:02,  3.99it/s]\n 71%|███████▏  | 20/28 [00:04<00:02,  3.99it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  3.99it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  3.98it/s]\n 82%|████████▏ | 23/28 [00:05<00:01,  3.98it/s]\n 86%|████████▌ | 24/28 [00:05<00:01,  3.98it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  3.98it/s]\n 93%|█████████▎| 26/28 [00:06<00:00,  3.99it/s]\n 96%|█████████▋| 27/28 [00:06<00:00,  3.99it/s]\n100%|██████████| 28/28 [00:06<00:00,  3.99it/s]\n100%|██████████| 28/28 [00:06<00:00,  4.01it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.04429792,
    "total_time": 8.063121
  },
  "output": [
    "https://replicate.delivery/xezq/baAJwGAxzfRPS6T4dtdqke1WrolYHjlZFgE5zCovrbfA1HaoA/out-0.png"
  ],
  "started_at": "2025-02-07T22:43:36.547823Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-xlobaboxvhkpqxaxrqkdr5rz5i6zp4pkb3mjgdr4qvoj7e2xqmxq",
    "get": "https://api.replicate.com/v1/predictions/th9j23hkt5rmc0cmwaat95a71w",
    "cancel": "https://api.replicate.com/v1/predictions/th9j23hkt5rmc0cmwaat95a71w/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

8.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

y9ntxh1h55rma0cmwacsd1nm0w

Status

Succeeded

Source

Web

Hardware

H100

Total duration

10.5s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. ",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green. ",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. ",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. ",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:48:08.489051Z",
  "created_at": "2025-02-07T22:47:57.993000Z",
  "data_removed": false,
  "error": null,
  "id": "y9ntxh1h55rma0cmwacsd1nm0w",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green. ",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Loaded LoRAs in 0.57s\nUsing seed: 33780\nPrompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green.\n[!] txt2img mode\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:06,  3.99it/s]\n  7%|▋         | 2/28 [00:00<00:05,  4.51it/s]\n 11%|█         | 3/28 [00:00<00:05,  4.26it/s]\n 14%|█▍        | 4/28 [00:00<00:05,  4.15it/s]\n 18%|█▊        | 5/28 [00:01<00:05,  4.10it/s]\n 21%|██▏       | 6/28 [00:01<00:05,  4.06it/s]\n 25%|██▌       | 7/28 [00:01<00:05,  4.04it/s]\n 29%|██▊       | 8/28 [00:01<00:04,  4.03it/s]\n 32%|███▏      | 9/28 [00:02<00:04,  4.02it/s]\n 36%|███▌      | 10/28 [00:02<00:04,  4.01it/s]\n 39%|███▉      | 11/28 [00:02<00:04,  4.01it/s]\n 43%|████▎     | 12/28 [00:02<00:03,  4.00it/s]\n 46%|████▋     | 13/28 [00:03<00:03,  4.00it/s]\n 50%|█████     | 14/28 [00:03<00:03,  4.00it/s]\n 54%|█████▎    | 15/28 [00:03<00:03,  4.00it/s]\n 57%|█████▋    | 16/28 [00:03<00:02,  4.00it/s]\n 61%|██████    | 17/28 [00:04<00:02,  4.00it/s]\n 64%|██████▍   | 18/28 [00:04<00:02,  4.00it/s]\n 68%|██████▊   | 19/28 [00:04<00:02,  4.00it/s]\n 71%|███████▏  | 20/28 [00:04<00:02,  4.00it/s]\n 75%|███████▌  | 21/28 [00:05<00:01,  4.00it/s]\n 79%|███████▊  | 22/28 [00:05<00:01,  4.00it/s]\n 82%|████████▏ | 23/28 [00:05<00:01,  4.00it/s]\n 86%|████████▌ | 24/28 [00:05<00:01,  4.00it/s]\n 89%|████████▉ | 25/28 [00:06<00:00,  4.00it/s]\n 93%|█████████▎| 26/28 [00:06<00:00,  4.00it/s]\n 96%|█████████▋| 27/28 [00:06<00:00,  4.00it/s]\n100%|██████████| 28/28 [00:06<00:00,  4.00it/s]\n100%|██████████| 28/28 [00:06<00:00,  4.03it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 8.036268635,
    "total_time": 10.496051
  },
  "output": [
    "https://replicate.delivery/xezq/2qAhFn4O35qXH9pShHUBWjNxn3HAPEt90j9sAMgjenWUfDNUA/out-0.png"
  ],
  "started_at": "2025-02-07T22:48:00.452782Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-pebrrua4c5su3sujtcliacowyppfasbpvfqsswzyvpxswaekpeja",
    "get": "https://api.replicate.com/v1/predictions/y9ntxh1h55rma0cmwacsd1nm0w",
    "cancel": "https://api.replicate.com/v1/predictions/y9ntxh1h55rma0cmwacsd1nm0w/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

8.0 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

gkmh08b9d5rme0cmwahv1sy038

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.0s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:59:10.797616Z",
  "created_at": "2025-02-07T22:59:07.753000Z",
  "data_removed": false,
  "error": null,
  "id": "gkmh08b9d5rme0cmwahv1sy038",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 2035472808\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.64it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.93it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.97it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.58it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.38it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.99it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.93it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.94it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.94it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.95it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.84it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.83it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.81it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.84it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.15it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.032014158,
    "total_time": 3.044616
  },
  "output": [
    "https://replicate.delivery/xezq/11hneg7vFejERkO1h0uaHkE8rvzYGEnoufNurAefmSUwHhohC/out-0.png"
  ],
  "started_at": "2025-02-07T22:59:07.765602Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-6rhoblcesayzhxhkvtis3bbkhneio3cwuepe3a7s4htdcbesrmjq",
    "get": "https://api.replicate.com/v1/predictions/gkmh08b9d5rme0cmwahv1sy038",
    "cancel": "https://api.replicate.com/v1/predictions/gkmh08b9d5rme0cmwahv1sy038/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.0 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

ahkp2pymp1rme0cmwahshzq42c

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.2s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:59:38.431613Z",
  "created_at": "2025-02-07T22:59:35.216000Z",
  "data_removed": false,
  "error": null,
  "id": "ahkp2pymp1rme0cmwahshzq42c",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 2861646718\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 16.72it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.62it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.68it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.31it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.00it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.63it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.61it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.63it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.65it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.61it/s]\n 79%|███████▊  | 22/28 [00:02<00:00, 10.45it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.45it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.51it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.57it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.83it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.094422848,
    "total_time": 3.215613
  },
  "output": [
    "https://replicate.delivery/xezq/OBM4LqEVn9rzCdfU0l4wBfzvie1s26DDwYS1zWQBG731SIaoA/out-0.png"
  ],
  "started_at": "2025-02-07T22:59:35.337190Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-lxp4oghueydazxve4jjnqqyddl5qhmfbxkegxb57l23ejlnoed3q",
    "get": "https://api.replicate.com/v1/predictions/ahkp2pymp1rme0cmwahshzq42c",
    "cancel": "https://api.replicate.com/v1/predictions/ahkp2pymp1rme0cmwahshzq42c/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

cv13vw96ehrma0cmwajbg0h5qm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.1s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T22:59:59.243552Z",
  "created_at": "2025-02-07T22:59:56.148000Z",
  "data_removed": false,
  "error": null,
  "id": "cv13vw96ehrma0cmwajbg0h5qm",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 4136897473\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.67it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.84it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.81it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.39it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.12it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.64it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.63it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.67it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.68it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.64it/s]\n 79%|███████▊  | 22/28 [00:02<00:00, 10.49it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.47it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.52it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.57it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.87it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.088555885,
    "total_time": 3.095552
  },
  "output": [
    "https://replicate.delivery/xezq/7tf4MDUio6S5IyP5gWva6i5ijfiYu1mbRk9QeJZYlYDemQ0QB/out-0.png"
  ],
  "started_at": "2025-02-07T22:59:56.154996Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-3mfn6mnxqzfsyaq2c6anentdha4vvuwvucjl7eana4jzgxrombmq",
    "get": "https://api.replicate.com/v1/predictions/cv13vw96ehrma0cmwajbg0h5qm",
    "cancel": "https://api.replicate.com/v1/predictions/cv13vw96ehrma0cmwajbg0h5qm/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

xxp8ehf4hnrma0cmwakbyrmh44

Status

Succeeded

Source

Web

Hardware

H100

Total duration

12.2s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:03:08.123577Z",
  "created_at": "2025-02-07T23:02:55.885000Z",
  "data_removed": false,
  "error": null,
  "id": "xxp8ehf4hnrma0cmwakbyrmh44",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 23:02:55.939 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 23:02:55.941 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=28600137670656\nDownloading weights\n2025-02-07T23:02:55Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpomx3jb64/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T23:03:04Z | INFO  | [ Complete ] dest=/tmp/tmpomx3jb64/weights size=\"215 MB\" total_elapsed=8.667s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 8.69s\n2025-02-07 23:03:04.635 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 23:03:04.715 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 23:03:04.715 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 23:03:04.715 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 124/304 [00:00<00:00, 1238.19it/s]\nApplying LoRA:  82%|████████▏ | 248/304 [00:00<00:00, 958.12it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 959.51it/s]\n2025-02-07 23:03:05.033 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 23:03:05.033 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 3769199527\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.28it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.82it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.82it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.42it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.09it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.83it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.80it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.80it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.80it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.73it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.63it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.60it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.67it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.70it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.98it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 12.204895797,
    "total_time": 12.238577
  },
  "output": [
    "https://replicate.delivery/xezq/j0LfAfvWOCke2IWVLn4M5GlW1LGK3jy7ut186iSrpp1ZZIaoA/out-0.png"
  ],
  "started_at": "2025-02-07T23:02:55.918682Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-x7zz7wvbyancmwdzgfqqy5ksz57ha43w6sapagbi7nfabvstn5sa",
    "get": "https://api.replicate.com/v1/predictions/xxp8ehf4hnrma0cmwakbyrmh44",
    "cancel": "https://api.replicate.com/v1/predictions/xxp8ehf4hnrma0cmwakbyrmh44/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

12.2 seconds

Tweak it Share Report

2025-02-07 23:02:55.939 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 23:02:55.941 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=28600137670656
Downloading weights
2025-02-07T23:02:55Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpomx3jb64/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T23:03:04Z | INFO  | [ Complete ] dest=/tmp/tmpomx3jb64/weights size="215 MB" total_elapsed=8.667s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 8.69s
2025-02-07 23:03:04.635 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 23:03:04.715 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 23:03:04.715 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 23:03:04.715 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████      | 124/304 [00:00<00:00, 1238.19it/s]
Applying LoRA:  82%|████████▏ | 248/304 [00:00<00:00, 958.12it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 959.51it/s]
2025-02-07 23:03:05.033 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 23:03:05.033 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 3769199527
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.28it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.82it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.82it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.42it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.09it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.83it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.80it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.80it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.80it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.73it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.63it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.60it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.67it/s]
100%|██████████| 28/28 [00:02<00:00, 10.70it/s]
100%|██████████| 28/28 [00:02<00:00, 10.98it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

a2sm2rys3drm80cmwam95qm34g

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.1s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:05:07.085863Z",
  "created_at": "2025-02-07T23:05:04.027000Z",
  "data_removed": false,
  "error": null,
  "id": "a2sm2rys3drm80cmwam95qm34g",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white and visible from front right side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 51859889\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.52it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.83it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.85it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.45it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.21it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.82it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.78it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.77it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.79it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.80it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.70it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.64it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.66it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.72it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.01it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.048160813,
    "total_time": 3.058863
  },
  "output": [
    "https://replicate.delivery/xezq/iNfPNIiUNF31c6UCExdAgpim3UeX5lTOD9vYArZIj71jOENUA/out-0.png"
  ],
  "started_at": "2025-02-07T23:05:04.037702Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-rstnhpr564b7sb5cjrg34z7ixvlrr52jryq4eelgk3fpmjdi7d5q",
    "get": "https://api.replicate.com/v1/predictions/a2sm2rys3drm80cmwam95qm34g",
    "cancel": "https://api.replicate.com/v1/predictions/a2sm2rys3drm80cmwam95qm34g/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.0 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

qb5htf3gk5rm80cmwanbg9byzr

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.1s

Created

4 months ago

Input

seed: 1364272806
model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "seed": 1364272806,
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      seed: 1364272806,
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "seed": 1364272806,
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "seed": 1364272806,
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:06:51.453291Z",
  "created_at": "2025-02-07T23:06:48.345000Z",
  "data_removed": false,
  "error": null,
  "id": "qb5htf3gk5rm80cmwanbg9byzr",
  "input": {
    "seed": 1364272806,
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 1364272806\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.83it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.74it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.71it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.26it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 10.95it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.64it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.61it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.59it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.59it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.54it/s]\n 79%|███████▊  | 22/28 [00:02<00:00, 10.41it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.42it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.47it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.50it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.80it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.10140049,
    "total_time": 3.108291
  },
  "output": [
    "https://replicate.delivery/xezq/ffamhr5DPbj5n0sTSmXAYqTfSEVJJPqotWKhXC2c6HmXgIaoA/out-0.png"
  ],
  "started_at": "2025-02-07T23:06:48.351890Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-743kzunswpbc64bkf6rfppscpixgvtwp7po556mvabh35qzsrs6q",
    "get": "https://api.replicate.com/v1/predictions/qb5htf3gk5rm80cmwanbg9byzr",
    "cancel": "https://api.replicate.com/v1/predictions/qb5htf3gk5rm80cmwanbg9byzr/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.1 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

ryv4j783jhrm80cmwap9ny88tc

Status

Succeeded

Source

Web

Hardware

H100

Total duration

5.3s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:08:36.807720Z",
  "created_at": "2025-02-07T23:08:31.508000Z",
  "data_removed": false,
  "error": null,
  "id": "ryv4j783jhrm80cmwap9ny88tc",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 23:08:31.551 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 23:08:31.552 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s\nfree=28936303935488\nDownloading weights\n2025-02-07T23:08:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbvovbnlz/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T23:08:33Z | INFO  | [ Complete ] dest=/tmp/tmpbvovbnlz/weights size=\"215 MB\" total_elapsed=1.738s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 1.76s\n2025-02-07 23:08:33.317 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 23:08:33.396 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 23:08:33.396 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 23:08:33.396 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 124/304 [00:00<00:00, 1228.46it/s]\nApplying LoRA:  81%|████████▏ | 247/304 [00:00<00:00, 977.18it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 971.31it/s]\n2025-02-07 23:08:33.709 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 23:08:33.710 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s\nrunning quantized prediction\nUsing seed: 2192376279\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.78it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.93it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.88it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.44it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.08it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.76it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.77it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.77it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.79it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.76it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.63it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.64it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.69it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.72it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.99it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 5.277998297,
    "total_time": 5.29972
  },
  "output": [
    "https://replicate.delivery/xezq/GwAYcCOzoIpJGlXIzzWO3kZo6UXHOgQJDuHHLoSElGHdERDF/out-0.png"
  ],
  "started_at": "2025-02-07T23:08:31.529721Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-7wwbpvnyjyrbuzt455gmliwwlksvzn4uy73kn57a54osg3veggpq",
    "get": "https://api.replicate.com/v1/predictions/ryv4j783jhrm80cmwap9ny88tc",
    "cancel": "https://api.replicate.com/v1/predictions/ryv4j783jhrm80cmwap9ny88tc/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

5.3 seconds

Tweak it Share Report

2025-02-07 23:08:31.551 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 23:08:31.552 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.024s
free=28936303935488
Downloading weights
2025-02-07T23:08:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbvovbnlz/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T23:08:33Z | INFO  | [ Complete ] dest=/tmp/tmpbvovbnlz/weights size="215 MB" total_elapsed=1.738s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 1.76s
2025-02-07 23:08:33.317 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 23:08:33.396 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 23:08:33.396 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 23:08:33.396 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  41%|████      | 124/304 [00:00<00:00, 1228.46it/s]
Applying LoRA:  81%|████████▏ | 247/304 [00:00<00:00, 977.18it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 971.31it/s]
2025-02-07 23:08:33.709 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 23:08:33.710 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s
running quantized prediction
Using seed: 2192376279
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.78it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.93it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.88it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.44it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.08it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.76it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.77it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.77it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.79it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.76it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.63it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.64it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.69it/s]
100%|██████████| 28/28 [00:02<00:00, 10.72it/s]
100%|██████████| 28/28 [00:02<00:00, 10.99it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

6y3tyvp1thrm80cmwapspcvf58

Status

Succeeded

Source

Web

Hardware

H100

Total duration

12.8s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:10:38.538050Z",
  "created_at": "2025-02-07T23:10:25.748000Z",
  "data_removed": false,
  "error": null,
  "id": "6y3tyvp1thrm80cmwapspcvf58",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from front side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 23:10:25.833 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 23:10:25.834 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s\nfree=28920611713024\nDownloading weights\n2025-02-07T23:10:25Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpw8387t1s/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T23:10:35Z | INFO  | [ Complete ] dest=/tmp/tmpw8387t1s/weights size=\"215 MB\" total_elapsed=9.180s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 9.23s\n2025-02-07 23:10:35.061 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 23:10:35.143 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 23:10:35.143 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 23:10:35.143 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  40%|████      | 123/304 [00:00<00:00, 1224.57it/s]\nApplying LoRA:  81%|████████  | 246/304 [00:00<00:00, 951.82it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 966.91it/s]\n2025-02-07 23:10:35.458 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 23:10:35.458 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s\nrunning quantized prediction\nUsing seed: 1555528026\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.47it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.95it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.94it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.52it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.17it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.84it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.84it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.86it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.89it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.86it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.74it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.73it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.77it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.80it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.07it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 12.726937058,
    "total_time": 12.79005
  },
  "output": [
    "https://replicate.delivery/xezq/509GiRoMeyRcMyD1rKu2vBZqSGkAWZyHN11iJlFVVDS3JiGKA/out-0.png"
  ],
  "started_at": "2025-02-07T23:10:25.811113Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-4aipjgd7puh2y2ybodata7rzgjt2gojffyrzfflaqfatkiax2qdq",
    "get": "https://api.replicate.com/v1/predictions/6y3tyvp1thrm80cmwapspcvf58",
    "cancel": "https://api.replicate.com/v1/predictions/6y3tyvp1thrm80cmwapspcvf58/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

12.7 seconds

Tweak it Share Report

2025-02-07 23:10:25.833 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 23:10:25.834 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.025s
free=28920611713024
Downloading weights
2025-02-07T23:10:25Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpw8387t1s/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T23:10:35Z | INFO  | [ Complete ] dest=/tmp/tmpw8387t1s/weights size="215 MB" total_elapsed=9.180s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 9.23s
2025-02-07 23:10:35.061 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 23:10:35.143 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 23:10:35.143 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 23:10:35.143 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  40%|████      | 123/304 [00:00<00:00, 1224.57it/s]
Applying LoRA:  81%|████████  | 246/304 [00:00<00:00, 951.82it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 966.91it/s]
2025-02-07 23:10:35.458 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 23:10:35.458 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.4s
running quantized prediction
Using seed: 1555528026
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.47it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.95it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.94it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.52it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.17it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.84it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.84it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.86it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.89it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.86it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.74it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.73it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.77it/s]
100%|██████████| 28/28 [00:02<00:00, 10.80it/s]
100%|██████████| 28/28 [00:02<00:00, 11.07it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

3tteqx9pj1rm80cmwaq974zss0

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.0s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:10:58.681306Z",
  "created_at": "2025-02-07T23:10:55.632000Z",
  "data_removed": false,
  "error": null,
  "id": "3tteqx9pj1rm80cmwaq974zss0",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the front side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 1664395363\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 18.24it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 13.11it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 12.00it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.55it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.31it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.89it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.85it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.86it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.87it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.88it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.76it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.75it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.79it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.80it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.11it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.043013098,
    "total_time": 3.049306
  },
  "output": [
    "https://replicate.delivery/xezq/rVMMteZtqQ1hCSalzLXeQ8uDz7Dzfu2k7ExhcJffwqKVgiohC/out-0.png"
  ],
  "started_at": "2025-02-07T23:10:55.638293Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-lk72chhxdh6nzi7t5ego2mt4cqxht3teyvz4trzy5ispnbrbjdta",
    "get": "https://api.replicate.com/v1/predictions/3tteqx9pj1rm80cmwaq974zss0",
    "cancel": "https://api.replicate.com/v1/predictions/3tteqx9pj1rm80cmwaq974zss0/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.0 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

1v18fzt7j5rm80cmwaqt3w6h7m

Status

Succeeded

Source

Web

Hardware

H100

Total duration

3.0s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:12:08.538917Z",
  "created_at": "2025-02-07T23:12:05.521000Z",
  "data_removed": false,
  "error": null,
  "id": "1v18fzt7j5rm80cmwaqt3w6h7m",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a city street. The tram is green and white. The tram is visible from the back side",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Lora https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar already loaded\nrunning quantized prediction\nUsing seed: 3788670906\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 18.16it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 13.10it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 12.02it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.58it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.34it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.95it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.92it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.90it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.89it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.89it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.79it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.76it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.80it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.83it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.13it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 3.010437662,
    "total_time": 3.017917
  },
  "output": [
    "https://replicate.delivery/xezq/LFIFuJIrNmbyFpTfjLbF0kuIzzUlkV2QrQHdYisfkNNIVENUA/out-0.png"
  ],
  "started_at": "2025-02-07T23:12:05.528479Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-i67r3s7wkp3deztsbv3v5f4anllc6pxpuacp6rzqoawccyn3z4xq",
    "get": "https://api.replicate.com/v1/predictions/1v18fzt7j5rm80cmwaqt3w6h7m",
    "cancel": "https://api.replicate.com/v1/predictions/1v18fzt7j5rm80cmwaqt3w6h7m/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

3.0 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

j6eb7t2efdrmc0cmwb8vh7qce0

Status

Succeeded

Source

Web

Hardware

H100

Total duration

4.8s

Created

4 months ago

Input

model: dev
width: 1024
height: 1024
prompt: A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue.
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue. ",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue. ",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue. ",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue. ",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-07T23:49:20.260083Z",
  "created_at": "2025-02-07T23:49:15.515000Z",
  "data_removed": false,
  "error": null,
  "id": "j6eb7t2efdrmc0cmwb8vh7qce0",
  "input": {
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram model tatra t3 TATRAT3 on a Mediterranean city street. The tram is green and blue. ",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "2025-02-07 23:49:15.621 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers\n2025-02-07 23:49:15.622 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.023s\nfree=5904957394944\nDownloading weights\n2025-02-07T23:49:15Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmprfcwoazm/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-07T23:49:16Z | INFO  | [ Complete ] dest=/tmp/tmprfcwoazm/weights size=\"215 MB\" total_elapsed=1.132s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 1.16s\n2025-02-07 23:49:16.780 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad\n2025-02-07 23:49:16.858 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded\n2025-02-07 23:49:16.858 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys\n2025-02-07 23:49:16.859 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  40%|████      | 123/304 [00:00<00:00, 1214.25it/s]\nApplying LoRA:  81%|████████  | 245/304 [00:00<00:00, 964.44it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 970.33it/s]\n2025-02-07 23:49:17.172 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8\n2025-02-07 23:49:17.172 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s\nrunning quantized prediction\nUsing seed: 1561267931\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 17.26it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.83it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.86it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.44it/s]\n 36%|███▌      | 10/28 [00:00<00:01, 11.13it/s]\n 43%|████▎     | 12/28 [00:01<00:01, 10.87it/s]\n 50%|█████     | 14/28 [00:01<00:01, 10.81it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.81it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.83it/s]\n 71%|███████▏  | 20/28 [00:01<00:00, 10.78it/s]\n 79%|███████▊  | 22/28 [00:01<00:00, 10.67it/s]\n 86%|████████▌ | 24/28 [00:02<00:00, 10.66it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.70it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.72it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.01it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 4.660416777,
    "total_time": 4.745083
  },
  "output": [
    "https://replicate.delivery/xezq/S1Xy79mKNH4XBZinbey8AegL50ebMxw2eJ3zeAeed1rXAciGKA/out-0.png"
  ],
  "started_at": "2025-02-07T23:49:15.599667Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-cjti5ekclbg52gfrdzhyydfizeegk7n5wll37hivtveiv6jynuvq",
    "get": "https://api.replicate.com/v1/predictions/j6eb7t2efdrmc0cmwb8vh7qce0",
    "cancel": "https://api.replicate.com/v1/predictions/j6eb7t2efdrmc0cmwb8vh7qce0/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

4.7 seconds

Tweak it Share Report

2025-02-07 23:49:15.621 | INFO     | fp8.lora_loading:restore_clones:592 - Unloaded 304 layers
2025-02-07 23:49:15.622 | SUCCESS  | fp8.lora_loading:unload_loras:563 - LoRAs unloaded in 0.023s
free=5904957394944
Downloading weights
2025-02-07T23:49:15Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmprfcwoazm/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-07T23:49:16Z | INFO  | [ Complete ] dest=/tmp/tmprfcwoazm/weights size="215 MB" total_elapsed=1.132s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 1.16s
2025-02-07 23:49:16.780 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/265dc36a7a34f2ad
2025-02-07 23:49:16.858 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-02-07 23:49:16.858 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:602 - Extracting keys
2025-02-07 23:49:16.859 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:609 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  40%|████      | 123/304 [00:00<00:00, 1214.25it/s]
Applying LoRA:  81%|████████  | 245/304 [00:00<00:00, 964.44it/s] 
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 970.33it/s]
2025-02-07 23:49:17.172 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:661 - Loading LoRA in fp8
2025-02-07 23:49:17.172 | SUCCESS  | fp8.lora_loading:load_lora:542 - LoRA applied in 0.39s
running quantized prediction
Using seed: 1561267931
  0%|          | 0/28 [00:00<?, ?it/s]
  7%|▋         | 2/28 [00:00<00:01, 17.26it/s]
 14%|█▍        | 4/28 [00:00<00:01, 12.83it/s]
 21%|██▏       | 6/28 [00:00<00:01, 11.86it/s]
 29%|██▊       | 8/28 [00:00<00:01, 11.44it/s]
 36%|███▌      | 10/28 [00:00<00:01, 11.13it/s]
 43%|████▎     | 12/28 [00:01<00:01, 10.87it/s]
 50%|█████     | 14/28 [00:01<00:01, 10.81it/s]
 57%|█████▋    | 16/28 [00:01<00:01, 10.81it/s]
 64%|██████▍   | 18/28 [00:01<00:00, 10.83it/s]
 71%|███████▏  | 20/28 [00:01<00:00, 10.78it/s]
 79%|███████▊  | 22/28 [00:01<00:00, 10.67it/s]
 86%|████████▌ | 24/28 [00:02<00:00, 10.66it/s]
 93%|█████████▎| 26/28 [00:02<00:00, 10.70it/s]
100%|██████████| 28/28 [00:02<00:00, 10.72it/s]
100%|██████████| 28/28 [00:02<00:00, 11.01it/s]
Total safe images: 1 out of 1

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

11jh7179wxrme0cmwvs8s07sac

Status

Succeeded

Source

Web

Hardware

H100

Total duration

7.8s

Created

4 months ago

Input

image
model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.5
extra_lora_scale: 1
num_inference_steps: 28

{
  "image": "https://replicate.delivery/pbxt/MSscG4DTsvrlJML6XfFd1U3JbuCjDm3rOB42qijufEEmkDok/1967-Centennial-3.jpg",
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.5,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      image: "https://replicate.delivery/pbxt/MSscG4DTsvrlJML6XfFd1U3JbuCjDm3rOB42qijufEEmkDok/1967-Centennial-3.jpg",
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street. A vintage photo. 60s",
      go_fast: true,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.5,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "image": "https://replicate.delivery/pbxt/MSscG4DTsvrlJML6XfFd1U3JbuCjDm3rOB42qijufEEmkDok/1967-Centennial-3.jpg",
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
        "go_fast": True,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.5,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "image": "https://replicate.delivery/pbxt/MSscG4DTsvrlJML6XfFd1U3JbuCjDm3rOB42qijufEEmkDok/1967-Centennial-3.jpg",
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.5,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-08T19:04:34.624198Z",
  "created_at": "2025-02-08T19:04:26.855000Z",
  "data_removed": false,
  "error": null,
  "id": "11jh7179wxrme0cmwvs8s07sac",
  "input": {
    "image": "https://replicate.delivery/pbxt/MSscG4DTsvrlJML6XfFd1U3JbuCjDm3rOB42qijufEEmkDok/1967-Centennial-3.jpg",
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
    "go_fast": true,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.5,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "Img2img and inpainting not supported with fast fp8 inference; will run in bf16\nfree=28152046182400\nDownloading weights\n2025-02-08T19:04:28Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpc9zp4coz/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-08T19:04:31Z | INFO  | [ Complete ] dest=/tmp/tmpc9zp4coz/weights size=\"215 MB\" total_elapsed=2.675s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 2.70s\nLoaded LoRAs in 3.27s\nUsing seed: 60731\nPrompt: A tram TATRAT3 running a street. A vintage photo. 60s\n[!] Resizing input image from 720x480 to 720x480\n[!] img2img mode\n  0%|          | 0/14 [00:00<?, ?it/s]\n  7%|▋         | 1/14 [00:00<00:10,  1.26it/s]\n 14%|█▍        | 2/14 [00:00<00:04,  2.54it/s]\n 21%|██▏       | 3/14 [00:01<00:02,  3.78it/s]\n 29%|██▊       | 4/14 [00:01<00:02,  4.89it/s]\n 36%|███▌      | 5/14 [00:01<00:01,  5.85it/s]\n 43%|████▎     | 6/14 [00:01<00:01,  6.64it/s]\n 50%|█████     | 7/14 [00:01<00:00,  7.25it/s]\n 57%|█████▋    | 8/14 [00:01<00:00,  7.72it/s]\n 64%|██████▍   | 9/14 [00:01<00:00,  8.07it/s]\n 71%|███████▏  | 10/14 [00:01<00:00,  8.33it/s]\n 79%|███████▊  | 11/14 [00:01<00:00,  8.51it/s]\n 86%|████████▌ | 12/14 [00:02<00:00,  8.64it/s]\n 93%|█████████▎| 13/14 [00:02<00:00,  8.73it/s]\n100%|██████████| 14/14 [00:02<00:00,  8.80it/s]\n100%|██████████| 14/14 [00:02<00:00,  6.23it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.160816626,
    "total_time": 7.769198
  },
  "output": [
    "https://replicate.delivery/xezq/0T2XbpF6XIozKFQVXuyK6SDJUCEylI3dbvRFNr9796twcVDF/out-0.png"
  ],
  "started_at": "2025-02-08T19:04:28.463381Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-wxzog3oitk6lzknsulpfsm5tasaj6v6tyiujja5iittmletpftra",
    "get": "https://api.replicate.com/v1/predictions/11jh7179wxrme0cmwvs8s07sac",
    "cancel": "https://api.replicate.com/v1/predictions/11jh7179wxrme0cmwvs8s07sac/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

6.2 seconds

Tweak it Share Report

Prediction

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4

Model

rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71

n253c60sp1rm80cmww49r929h4

Status

Succeeded

Source

Web

Hardware

H100

Total duration

7.1s

Created

4 months ago

Input

mask
image
model: dev
width: 1024
height: 1024
prompt: A tram TATRAT3 running a street. A vintage photo. 60s
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 1
aspect_ratio: 1:1
output_format: png
guidance_scale: 3
output_quality: 80
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
  "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
  "model": "dev",
  "width": 1024,
  "height": 1024,
  "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  {
    input: {
      mask: "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      image: "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      model: "dev",
      width: 1024,
      height: 1024,
      prompt: "A tram TATRAT3 running a street. A vintage photo. 60s",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 1,
      aspect_ratio: "1:1",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 80,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    input={
        "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
        "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
        "model": "dev",
        "width": 1024,
        "height": 1024,
        "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 1,
        "aspect_ratio": "1:1",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 80,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run rinatkurmaev/flux-dev-lora-tatra-t3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "rinatkurmaev/flux-dev-lora-tatra-t3:25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
    "input": {
      "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
      "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
      "model": "dev",
      "width": 1024,
      "height": 1024,
      "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 80,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-02-08T19:27:42.418015Z",
  "created_at": "2025-02-08T19:27:35.344000Z",
  "data_removed": false,
  "error": null,
  "id": "n253c60sp1rm80cmww49r929h4",
  "input": {
    "mask": "https://replicate.delivery/pbxt/MSsviUPBa1U7ABxnhOumqGNrH9nGysUDWUmeNVo7CnAV1rmH/mask.png",
    "image": "https://replicate.delivery/pbxt/MSsnc5WTWaMcrPp6zvQkCljV9V41JG104YdkMdHUfzHPSmV6/1967-Centennial-3.jpg",
    "model": "dev",
    "width": 1024,
    "height": 1024,
    "prompt": "A tram TATRAT3 running a street. A vintage photo. 60s",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 80,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "free=28302063566848\nDownloading weights\n2025-02-08T19:27:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpksqux536/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\n2025-02-08T19:27:38Z | INFO  | [ Complete ] dest=/tmp/tmpksqux536/weights size=\"215 MB\" total_elapsed=2.220s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar\nDownloaded weights in 2.25s\nLoaded LoRAs in 2.81s\nUsing seed: 25700\nPrompt: A tram TATRAT3 running a street. A vintage photo. 60s\n[!] Resizing input image from 720x480 to 720x480\n[!] inpaint mode\n  0%|          | 0/23 [00:00<?, ?it/s]\n  4%|▍         | 1/23 [00:00<00:17,  1.24it/s]\n  9%|▊         | 2/23 [00:00<00:08,  2.50it/s]\n 13%|█▎        | 3/23 [00:01<00:05,  3.72it/s]\n 17%|█▋        | 4/23 [00:01<00:03,  4.82it/s]\n 22%|██▏       | 5/23 [00:01<00:03,  5.76it/s]\n 26%|██▌       | 6/23 [00:01<00:02,  6.53it/s]\n 30%|███       | 7/23 [00:01<00:02,  7.13it/s]\n 35%|███▍      | 8/23 [00:01<00:01,  7.60it/s]\n 39%|███▉      | 9/23 [00:01<00:01,  7.94it/s]\n 43%|████▎     | 10/23 [00:01<00:01,  8.19it/s]\n 48%|████▊     | 11/23 [00:01<00:01,  8.37it/s]\n 52%|█████▏    | 12/23 [00:02<00:01,  8.50it/s]\n 57%|█████▋    | 13/23 [00:02<00:01,  8.60it/s]\n 61%|██████    | 14/23 [00:02<00:01,  8.66it/s]\n 65%|██████▌   | 15/23 [00:02<00:00,  8.70it/s]\n 70%|██████▉   | 16/23 [00:02<00:00,  8.73it/s]\n 74%|███████▍  | 17/23 [00:02<00:00,  8.76it/s]\n 78%|███████▊  | 18/23 [00:02<00:00,  8.77it/s]\n 83%|████████▎ | 19/23 [00:02<00:00,  8.79it/s]\n 87%|████████▋ | 20/23 [00:02<00:00,  8.80it/s]\n 91%|█████████▏| 21/23 [00:03<00:00,  8.80it/s]\n 96%|█████████▌| 22/23 [00:03<00:00,  8.81it/s]\n100%|██████████| 23/23 [00:03<00:00,  7.01it/s]\nTotal safe images: 1 out of 1",
  "metrics": {
    "predict_time": 6.73930896,
    "total_time": 7.074015
  },
  "output": [
    "https://replicate.delivery/xezq/1LVJIhQFAKZnP1hpEy7q4KKvIXa3YVp08VxYUbhNRjgLiVDF/out-0.png"
  ],
  "started_at": "2025-02-08T19:27:35.678706Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-mrqobmlqg6ncoyqditts7qy5xkm7o43x3wcccfv4ark5zi5gr34a",
    "get": "https://api.replicate.com/v1/predictions/n253c60sp1rm80cmww49r929h4",
    "cancel": "https://api.replicate.com/v1/predictions/n253c60sp1rm80cmww49r929h4/cancel"
  },
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4"
}

Generated in

6.7 seconds

Tweak it Share Report

free=28302063566848
Downloading weights
2025-02-08T19:27:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpksqux536/weights url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
2025-02-08T19:27:38Z | INFO  | [ Complete ] dest=/tmp/tmpksqux536/weights size="215 MB" total_elapsed=2.220s url=https://replicate.delivery/xezq/5wg4NzY5IOIuMZ4bhf8BTSUhf8hq4vj2AWECTkhWETqANDNUA/trained_model.tar
Downloaded weights in 2.25s
Loaded LoRAs in 2.81s
Using seed: 25700
Prompt: A tram TATRAT3 running a street. A vintage photo. 60s
[!] Resizing input image from 720x480 to 720x480
[!] inpaint mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:17,  1.24it/s]
  9%|▊         | 2/23 [00:00<00:08,  2.50it/s]
 13%|█▎        | 3/23 [00:01<00:05,  3.72it/s]
 17%|█▋        | 4/23 [00:01<00:03,  4.82it/s]
 22%|██▏       | 5/23 [00:01<00:03,  5.76it/s]
 26%|██▌       | 6/23 [00:01<00:02,  6.53it/s]
 30%|███       | 7/23 [00:01<00:02,  7.13it/s]
 35%|███▍      | 8/23 [00:01<00:01,  7.60it/s]
 39%|███▉      | 9/23 [00:01<00:01,  7.94it/s]
 43%|████▎     | 10/23 [00:01<00:01,  8.19it/s]
 48%|████▊     | 11/23 [00:01<00:01,  8.37it/s]
 52%|█████▏    | 12/23 [00:02<00:01,  8.50it/s]
 57%|█████▋    | 13/23 [00:02<00:01,  8.60it/s]
 61%|██████    | 14/23 [00:02<00:01,  8.66it/s]
 65%|██████▌   | 15/23 [00:02<00:00,  8.70it/s]
 70%|██████▉   | 16/23 [00:02<00:00,  8.73it/s]
 74%|███████▍  | 17/23 [00:02<00:00,  8.76it/s]
 78%|███████▊  | 18/23 [00:02<00:00,  8.77it/s]
 83%|████████▎ | 19/23 [00:02<00:00,  8.79it/s]
 87%|████████▋ | 20/23 [00:02<00:00,  8.80it/s]
 91%|█████████▏| 21/23 [00:03<00:00,  8.80it/s]
 96%|█████████▌| 22/23 [00:03<00:00,  8.81it/s]
100%|██████████| 23/23 [00:03<00:00,  7.01it/s]
Total safe images: 1 out of 1

Want to make some of these yourself?

Run this model