Prediction

Official model

black-forest-labs/flux-dev-lora

55tgxa28qxrm80ck50996j6yzg

Status

Succeeded

Source

Web

Total duration

3.4s

Created

about 1 year ago

Webhook

–

Input

prompt: A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style
aspect_ratio: 1:1
prompt_strength: 0.8
num_outputs: 1
num_inference_steps: 28
guidance: 3
output_format: webp
output_quality: 80
go_fast: true
lora_weights: huggingface.co/alvdansen/flux-koda
lora_scale: 0.9
megapixels: 1

{
  "aspect_ratio": "1:1",
  "go_fast": true,
  "guidance": 3,
  "lora_scale": 0.9,
  "lora_weights": "huggingface.co/alvdansen/flux-koda",
  "megapixels": "1",
  "num_inference_steps": 28,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 80,
  "prompt": "A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style",
  "prompt_strength": 0.8
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_DZD**********************************

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 black-forest-labs/flux-dev-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  aspect_ratio: "1:1",
  go_fast: true,
  guidance: 3,
  lora_scale: 0.9,
  lora_weights: "huggingface.co/alvdansen/flux-koda",
  megapixels: "1",
  num_inference_steps: 28,
  num_outputs: 1,
  output_format: "webp",
  output_quality: 80,
  prompt: "A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style",
  prompt_strength: 0.8
};

const output = await replicate.run("black-forest-labs/flux-dev-lora", { input });

// 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_DZD**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

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

output = replicate.run(
    "black-forest-labs/flux-dev-lora",
    input={
        "aspect_ratio": "1:1",
        "go_fast": True,
        "guidance": 3,
        "lora_scale": 0.9,
        "lora_weights": "huggingface.co/alvdansen/flux-koda",
        "megapixels": "1",
        "num_inference_steps": 28,
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 80,
        "prompt": "A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style",
        "prompt_strength": 0.8
    }
)

# 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_DZD**********************************

This is your API token. Keep it to yourself.

Run black-forest-labs/flux-dev-lora 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 $'{
    "input": {
      "aspect_ratio": "1:1",
      "go_fast": true,
      "guidance": 3,
      "lora_scale": 0.9,
      "lora_weights": "huggingface.co/alvdansen/flux-koda",
      "megapixels": "1",
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 80,
      "prompt": "A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style",
      "prompt_strength": 0.8
    }
  }' \
  https://api.replicate.com/v1/models/black-forest-labs/flux-dev-lora/predictions

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

Output

{
  "id": "55tgxa28qxrm80ck50996j6yzg",
  "model": "black-forest-labs/flux-dev-lora",
  "version": "hidden",
  "input": {
    "aspect_ratio": "1:1",
    "go_fast": true,
    "guidance": 3,
    "lora_scale": 0.9,
    "lora_weights": "huggingface.co/alvdansen/flux-koda",
    "megapixels": "1",
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 80,
    "prompt": "A tabby cat lounging on a sun-dappled windowsill, half its body in shadow, half in bright light, flmft style",
    "prompt_strength": 0.8
  },
  "logs": "2024-11-14 00:28:27.205 | DEBUG    | fp8.lora_loading:apply_lora_to_model:547 - Extracting keys\n2024-11-14 00:28:27.205 | DEBUG    | fp8.lora_loading:apply_lora_to_model:554 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 13354.16it/s]\n2024-11-14 00:28:27.228 | SUCCESS  | fp8.lora_loading:unload_loras:537 - LoRAs unloaded in 0.023s\n2024-11-14 00:28:27.231 | INFO     | fp8.lora_loading:load_lora:497 - Loading LoRA weights for /src/weights-cache/31eaaa0241aa1ad5\n2024-11-14 00:28:27.384 | INFO     | fp8.lora_loading:load_lora:518 - LoRA weights loaded\n2024-11-14 00:28:27.384 | DEBUG    | fp8.lora_loading:apply_lora_to_model:547 - Extracting keys\n2024-11-14 00:28:27.384 | DEBUG    | fp8.lora_loading:apply_lora_to_model:554 - Keys extracted\nApplying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]\nApplying LoRA:  41%|████      | 125/304 [00:00<00:00, 1248.30it/s]\nApplying LoRA:  82%|████████▏ | 250/304 [00:00<00:00, 954.60it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 967.09it/s]\n2024-11-14 00:28:27.699 | SUCCESS  | fp8.lora_loading:load_lora:521 - LoRA applied in 0.47s\nrunning quantized prediction\nUsing seed: 1541013700\n  0%|          | 0/28 [00:00<?, ?it/s]\n  7%|▋         | 2/28 [00:00<00:01, 18.02it/s]\n 14%|█▍        | 4/28 [00:00<00:01, 12.97it/s]\n 21%|██▏       | 6/28 [00:00<00:01, 11.90it/s]\n 29%|██▊       | 8/28 [00:00<00:01, 11.47it/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, 10.83it/s]\n 57%|█████▋    | 16/28 [00:01<00:01, 10.82it/s]\n 64%|██████▍   | 18/28 [00:01<00:00, 10.82it/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, 10.69it/s]\n 93%|█████████▎| 26/28 [00:02<00:00, 10.73it/s]\n100%|██████████| 28/28 [00:02<00:00, 10.73it/s]\n100%|██████████| 28/28 [00:02<00:00, 11.03it/s]\nTotal safe images: 1 out of 1",
  "output": [
    "https://replicate.delivery/xezq/YumehO0CBftCZUz9ubFKRXBGU3ZOePKrD7TivvfeUOW1F7FeE/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-11-14T00:28:27.199Z",
  "started_at": "2024-11-14T00:28:27.204799Z",
  "completed_at": "2024-11-14T00:28:30.579241Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/55tgxa28qxrm80ck50996j6yzg/cancel",
    "get": "https://api.replicate.com/v1/predictions/55tgxa28qxrm80ck50996j6yzg",
    "stream": "https://stream.replicate.com/v1/files/bcwr-4p76hgchoqzr65twu5srquso5xyww7i2veovf3hngdxdlp6nwkja",
    "web": "https://replicate.com/p/55tgxa28qxrm80ck50996j6yzg"
  },
  "metrics": {
    "image_count": 1,
    "predict_time": 3.374442034,
    "total_time": 3.380241
  }
}

Generated in

3.4 seconds

Tweak it Iterate in playground Report

2024-11-14 00:28:27.205 | DEBUG | fp8.lora_loading:apply_lora_to_model:547 - Extracting keys 2024-11-14 00:28:27.205 | DEBUG | fp8.lora_loading:apply_lora_to_model:554 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 13354.16it/s] 2024-11-14 00:28:27.228 | SUCCESS | fp8.lora_loading:unload_loras:537 - LoRAs unloaded in 0.023s 2024-11-14 00:28:27.231 | INFO | fp8.lora_loading:load_lora:497 - Loading LoRA weights for /src/weights-cache/31eaaa0241aa1ad5 2024-11-14 00:28:27.384 | INFO | fp8.lora_loading:load_lora:518 - LoRA weights loaded 2024-11-14 00:28:27.384 | DEBUG | fp8.lora_loading:apply_lora_to_model:547 - Extracting keys 2024-11-14 00:28:27.384 | DEBUG | fp8.lora_loading:apply_lora_to_model:554 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 41%|████ | 125/304 [00:00<00:00, 1248.30it/s] Applying LoRA: 82%|████████▏ | 250/304 [00:00<00:00, 954.60it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 967.09it/s] 2024-11-14 00:28:27.699 | SUCCESS | fp8.lora_loading:load_lora:521 - LoRA applied in 0.47s running quantized prediction Using seed: 1541013700 0%| | 0/28 [00:00<?, ?it/s] 7%|▋ | 2/28 [00:00<00:01, 18.02it/s] 14%|█▍ | 4/28 [00:00<00:01, 12.97it/s] 21%|██▏ | 6/28 [00:00<00:01, 11.90it/s] 29%|██▊ | 8/28 [00:00<00:01, 11.47it/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, 10.83it/s] 57%|█████▋ | 16/28 [00:01<00:01, 10.82it/s] 64%|██████▍ | 18/28 [00:01<00:00, 10.82it/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, 10.69it/s] 93%|█████████▎| 26/28 [00:02<00:00, 10.73it/s] 100%|██████████| 28/28 [00:02<00:00, 10.73it/s] 100%|██████████| 28/28 [00:02<00:00, 11.03it/s] Total safe images: 1 out of 1