Prediction

Model

lucataco/flux-dev-lora:c0702494

mwp3k848ksrj60chs708m97jxm

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

16.8s

Created

over 1 year ago by lucataco

Webhook

–

Input

prompt: portrait photo of TOK with purple hair
aspect_ratio: 1:1
image: https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png
prompt_strength: 0.8
num_outputs: 1
num_inference_steps: 28
guidance_scale: 3.5
output_format: webp
output_quality: 80
hf_lora: https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar
lora_scale: 0.8

{
  "aspect_ratio": "1:1",
  "guidance_scale": 3.5,
  "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
  "image": "https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png",
  "lora_scale": 0.8,
  "num_inference_steps": 28,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 80,
  "prompt": "portrait photo of TOK with purple hair",
  "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_daV**********************************

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

const output = await replicate.run(
  "lucataco/flux-dev-lora:c0702494406cf8cc4d69490f2b464a993e9c9e99731640ebfc22ec09eb94276a",
  {
    input: {
      aspect_ratio: "1:1",
      guidance_scale: 3.5,
      hf_lora: "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
      image: "https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png",
      lora_scale: 0.8,
      num_inference_steps: 28,
      num_outputs: 1,
      output_format: "webp",
      output_quality: 80,
      prompt: "portrait photo of TOK with purple hair",
      prompt_strength: 0.8
    }
  }
);

// 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_daV**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

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

output = replicate.run(
    "lucataco/flux-dev-lora:c0702494406cf8cc4d69490f2b464a993e9c9e99731640ebfc22ec09eb94276a",
    input={
        "aspect_ratio": "1:1",
        "guidance_scale": 3.5,
        "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
        "image": "https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png",
        "lora_scale": 0.8,
        "num_inference_steps": 28,
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 80,
        "prompt": "portrait photo of TOK with purple hair",
        "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_daV**********************************

This is your API token. Keep it to yourself.

Run lucataco/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 $'{
    "version": "lucataco/flux-dev-lora:c0702494406cf8cc4d69490f2b464a993e9c9e99731640ebfc22ec09eb94276a",
    "input": {
      "aspect_ratio": "1:1",
      "guidance_scale": 3.5,
      "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
      "image": "https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png",
      "lora_scale": 0.8,
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 80,
      "prompt": "portrait photo of TOK with purple hair",
      "prompt_strength": 0.8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "mwp3k848ksrj60chs708m97jxm",
  "model": "lucataco/flux-dev-lora",
  "version": "c0702494406cf8cc4d69490f2b464a993e9c9e99731640ebfc22ec09eb94276a",
  "input": {
    "aspect_ratio": "1:1",
    "guidance_scale": 3.5,
    "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
    "image": "https://replicate.delivery/pbxt/LZvsjQcYuNfdmYuXETyePkaXNPCydRs4NJd9Nj4uSTVVQ0SO/image.png",
    "lora_scale": 0.8,
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 80,
    "prompt": "portrait photo of TOK with purple hair",
    "prompt_strength": 0.8
  },
  "logs": "Using seed: 44517\nPrompt: portrait photo of TOK with purple hair\nimg2img mode\nInput image size: 680x680\nInput image size set to: 688x688\nDownloading LoRA weights from - Replicate URL: https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\nEnsuring enough disk space...\nDownloading weights: https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\n2024-09-06T23:52:04Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3183c8e9c43647c8 url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\n2024-09-06T23:52:05Z | INFO  | [ Complete ] dest=/src/weights-cache/3183c8e9c43647c8 size=\"172 MB\" total_elapsed=1.462s url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\nb''\nDownloaded weights in 1.4893417358398438 seconds\nLoading LoRA took: 3.22 seconds\n/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/configuration_utils.py:140: FutureWarning: Accessing config attribute `vae_latent_channels` directly via 'VaeImageProcessor' object attribute is deprecated. Please access 'vae_latent_channels' over 'VaeImageProcessor's config object instead, e.g. 'scheduler.config.vae_latent_channels'.\ndeprecate(\"direct config name access\", \"1.0.0\", deprecation_message, standard_warn=False)\n/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/image_processor.py:582: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0]\nwarnings.warn(\n  0%|          | 0/23 [00:00<?, ?it/s]\n  4%|▍         | 1/23 [00:00<00:09,  2.29it/s]\n  9%|▊         | 2/23 [00:00<00:10,  2.01it/s]\n 13%|█▎        | 3/23 [00:01<00:10,  1.93it/s]\n 17%|█▋        | 4/23 [00:02<00:10,  1.89it/s]\n 22%|██▏       | 5/23 [00:02<00:09,  1.87it/s]\n 26%|██▌       | 6/23 [00:03<00:09,  1.86it/s]\n 30%|███       | 7/23 [00:03<00:08,  1.85it/s]\n 35%|███▍      | 8/23 [00:04<00:08,  1.85it/s]\n 39%|███▉      | 9/23 [00:04<00:07,  1.85it/s]\n 43%|████▎     | 10/23 [00:05<00:07,  1.84it/s]\n 48%|████▊     | 11/23 [00:05<00:06,  1.84it/s]\n 52%|█████▏    | 12/23 [00:06<00:05,  1.84it/s]\n 57%|█████▋    | 13/23 [00:06<00:05,  1.84it/s]\n 61%|██████    | 14/23 [00:07<00:04,  1.84it/s]\n 65%|██████▌   | 15/23 [00:08<00:04,  1.84it/s]\n 70%|██████▉   | 16/23 [00:08<00:03,  1.84it/s]\n 74%|███████▍  | 17/23 [00:09<00:03,  1.84it/s]\n 78%|███████▊  | 18/23 [00:09<00:02,  1.84it/s]\n 83%|████████▎ | 19/23 [00:10<00:02,  1.84it/s]\n 87%|████████▋ | 20/23 [00:10<00:01,  1.84it/s]\n 91%|█████████▏| 21/23 [00:11<00:01,  1.84it/s]\n 96%|█████████▌| 22/23 [00:11<00:00,  1.84it/s]\n100%|██████████| 23/23 [00:12<00:00,  1.84it/s]\n100%|██████████| 23/23 [00:12<00:00,  1.85it/s]",
  "output": [
    "https://replicate.delivery/yhqm/aWg8rzL8K5J6AZL1ZIPv9fpODQttgYdenTPx5syASmi0eo0mA/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-09-06T23:52:03.998Z",
  "started_at": "2024-09-06T23:52:04.007838Z",
  "completed_at": "2024-09-06T23:52:20.776381Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/mwp3k848ksrj60chs708m97jxm/cancel",
    "get": "https://api.replicate.com/v1/predictions/mwp3k848ksrj60chs708m97jxm",
    "web": "https://replicate.com/p/mwp3k848ksrj60chs708m97jxm"
  },
  "metrics": {
    "predict_time": 16.768542524,
    "total_time": 16.778381
  }
}

Generated in

16.8 seconds

Tweak it Report

Using seed: 44517 Prompt: portrait photo of TOK with purple hair img2img mode Input image size: 680x680 Input image size set to: 688x688 Downloading LoRA weights from - Replicate URL: https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar Ensuring enough disk space... Downloading weights: https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar 2024-09-06T23:52:04Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3183c8e9c43647c8 url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar 2024-09-06T23:52:05Z | INFO | [ Complete ] dest=/src/weights-cache/3183c8e9c43647c8 size="172 MB" total_elapsed=1.462s url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar b'' Downloaded weights in 1.4893417358398438 seconds Loading LoRA took: 3.22 seconds /root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/configuration_utils.py:140: FutureWarning: Accessing config attribute `vae_latent_channels` directly via 'VaeImageProcessor' object attribute is deprecated. Please access 'vae_latent_channels' over 'VaeImageProcessor's config object instead, e.g. 'scheduler.config.vae_latent_channels'. deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False) /root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/image_processor.py:582: FutureWarning: Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] when passing as pytorch tensor or numpy Array. You passed `image` with value range [-1.0,1.0] warnings.warn( 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:09, 2.29it/s] 9%|▊ | 2/23 [00:00<00:10, 2.01it/s] 13%|█▎ | 3/23 [00:01<00:10, 1.93it/s] 17%|█▋ | 4/23 [00:02<00:10, 1.89it/s] 22%|██▏ | 5/23 [00:02<00:09, 1.87it/s] 26%|██▌ | 6/23 [00:03<00:09, 1.86it/s] 30%|███ | 7/23 [00:03<00:08, 1.85it/s] 35%|███▍ | 8/23 [00:04<00:08, 1.85it/s] 39%|███▉ | 9/23 [00:04<00:07, 1.85it/s] 43%|████▎ | 10/23 [00:05<00:07, 1.84it/s] 48%|████▊ | 11/23 [00:05<00:06, 1.84it/s] 52%|█████▏ | 12/23 [00:06<00:05, 1.84it/s] 57%|█████▋ | 13/23 [00:06<00:05, 1.84it/s] 61%|██████ | 14/23 [00:07<00:04, 1.84it/s] 65%|██████▌ | 15/23 [00:08<00:04, 1.84it/s] 70%|██████▉ | 16/23 [00:08<00:03, 1.84it/s] 74%|███████▍ | 17/23 [00:09<00:03, 1.84it/s] 78%|███████▊ | 18/23 [00:09<00:02, 1.84it/s] 83%|████████▎ | 19/23 [00:10<00:02, 1.84it/s] 87%|████████▋ | 20/23 [00:10<00:01, 1.84it/s] 91%|█████████▏| 21/23 [00:11<00:01, 1.84it/s] 96%|█████████▌| 22/23 [00:11<00:00, 1.84it/s] 100%|██████████| 23/23 [00:12<00:00, 1.84it/s] 100%|██████████| 23/23 [00:12<00:00, 1.85it/s]