Prediction

Model

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

ng0q524b89rm80cmwa397n1sdm

Status

Succeeded

Source

Web

Hardware

H100

Total duration

6.6s

Created

10 months ago

Webhook

–

Input

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

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

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_6FI**********************************

This is your API token. Keep it to yourself.

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

// 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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_6FI**********************************

This is your API token. Keep it to yourself.

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

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_6FI**********************************

This is your API token. Keep it to yourself.

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": {
      "aspect_ratio": "1:1",
      "extra_lora_scale": 1,
      "go_fast": true,
      "guidance_scale": 3,
      "height": 1024,
      "lora_scale": 1,
      "megapixels": "1",
      "model": "dev",
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "png",
      "output_quality": 80,
      "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\\nThe snowy mountains are on the background",
      "prompt_strength": 0.8,
      "seed": 256,
      "width": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "ng0q524b89rm80cmwa397n1sdm",
  "model": "rinatkurmaev/flux-dev-lora-tatra-t3",
  "version": "25b2bc71bd11c42a9e7ce2f91995ded93cc12f1f23d2cbb7fff77f3da1bb65c4",
  "input": {
    "aspect_ratio": "1:1",
    "extra_lora_scale": 1,
    "go_fast": true,
    "guidance_scale": 3,
    "height": 1024,
    "lora_scale": 1,
    "megapixels": "1",
    "model": "dev",
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "png",
    "output_quality": 80,
    "prompt": "A tram model tatra t3 on a city street. The tram is green and red.\nThe snowy mountains are on the background",
    "prompt_strength": 0.8,
    "seed": 256,
    "width": 1024
  },
  "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",
  "output": [
    "https://replicate.delivery/xezq/fMpYkC7rRoyGJKQ7LeoEpXIdewfbpZXI6evntmR28HpxbdohC/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-02-07T22:27:35.874Z",
  "started_at": "2025-02-07T22:27:35.884656Z",
  "completed_at": "2025-02-07T22:27:42.481446Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/ng0q524b89rm80cmwa397n1sdm/cancel",
    "get": "https://api.replicate.com/v1/predictions/ng0q524b89rm80cmwa397n1sdm",
    "stream": "https://stream.replicate.com/v1/files/bcwr-j6uvwyb5hw75c2je6apotpamhhjt5mpg3wbaw2ztvkvuqixgloca",
    "web": "https://replicate.com/p/ng0q524b89rm80cmwa397n1sdm"
  },
  "metrics": {
    "predict_time": 6.596790403,
    "total_time": 6.607446
  }
}

Generated in

6.6 seconds

Tweak it 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