Prediction

Model

lucataco/flux-dev-lora:a22c463f

x71fmj0jb1rj00che4pa5j2xnc

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

18.5s

Created

over 1 year ago by lucataco

Webhook

–

Input

prompt: a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text "Replicate" Behind her, there is a presentation with the text "How I made 100k MRR"
aspect_ratio: 1:1
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",
  "lora_scale": 0.8,
  "num_inference_steps": 28,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 80,
  "prompt": "a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \"Replicate\"\n\nBehind her, there is a presentation with the text \"How I made 100k MRR\""
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_I6W**********************************

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:a22c463f11808638ad5e2ebd582e07a469031f48dd567366fb4c6fdab91d614d",
  {
    input: {
      aspect_ratio: "1:1",
      guidance_scale: 3.5,
      hf_lora: "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
      lora_scale: 0.8,
      num_inference_steps: 28,
      num_outputs: 1,
      output_format: "webp",
      output_quality: 80,
      prompt: "a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \"Replicate\"\n\nBehind her, there is a presentation with the text \"How I made 100k MRR\""
    }
  }
);

// 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_I6W**********************************

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:a22c463f11808638ad5e2ebd582e07a469031f48dd567366fb4c6fdab91d614d",
    input={
        "aspect_ratio": "1:1",
        "guidance_scale": 3.5,
        "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
        "lora_scale": 0.8,
        "num_inference_steps": 28,
        "num_outputs": 1,
        "output_format": "webp",
        "output_quality": 80,
        "prompt": "a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \"Replicate\"\n\nBehind her, there is a presentation with the text \"How I made 100k MRR\""
    }
)

# 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_I6W**********************************

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:a22c463f11808638ad5e2ebd582e07a469031f48dd567366fb4c6fdab91d614d",
    "input": {
      "aspect_ratio": "1:1",
      "guidance_scale": 3.5,
      "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
      "lora_scale": 0.8,
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "webp",
      "output_quality": 80,
      "prompt": "a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She\'s also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \\"Replicate\\"\\n\\nBehind her, there is a presentation with the text \\"How I made 100k MRR\\""
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "x71fmj0jb1rj00che4pa5j2xnc",
  "model": "lucataco/flux-dev-lora",
  "version": "a22c463f11808638ad5e2ebd582e07a469031f48dd567366fb4c6fdab91d614d",
  "input": {
    "aspect_ratio": "1:1",
    "guidance_scale": 3.5,
    "hf_lora": "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
    "lora_scale": 0.8,
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "webp",
    "output_quality": 80,
    "prompt": "a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \"Replicate\"\n\nBehind her, there is a presentation with the text \"How I made 100k MRR\""
  },
  "logs": "Using seed: 11405\nPrompt: a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text \"Replicate\"\nBehind her, there is a presentation with the text \"How I made 100k MRR\"\ntxt2img mode\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\n2024-08-20T19:03:19Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3183c8e9c43647c8 url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\n2024-08-20T19:03:20Z | INFO  | [ Complete ] dest=/src/weights-cache/3183c8e9c43647c8 size=\"172 MB\" total_elapsed=1.109s url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar\nb''\nDownloaded weights in 1.1337289810180664 seconds\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k mrr \"']\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:14,  1.88it/s]\n  7%|▋         | 2/28 [00:00<00:11,  2.18it/s]\n 11%|█         | 3/28 [00:01<00:12,  2.03it/s]\n 14%|█▍        | 4/28 [00:02<00:12,  1.96it/s]\n 18%|█▊        | 5/28 [00:02<00:11,  1.93it/s]\n 21%|██▏       | 6/28 [00:03<00:11,  1.91it/s]\n 25%|██▌       | 7/28 [00:03<00:11,  1.90it/s]\n 29%|██▊       | 8/28 [00:04<00:10,  1.89it/s]\n 32%|███▏      | 9/28 [00:04<00:10,  1.88it/s]\n 36%|███▌      | 10/28 [00:05<00:09,  1.88it/s]\n 39%|███▉      | 11/28 [00:05<00:09,  1.88it/s]\n 43%|████▎     | 12/28 [00:06<00:08,  1.88it/s]\n 46%|████▋     | 13/28 [00:06<00:08,  1.87it/s]\n 50%|█████     | 14/28 [00:07<00:07,  1.87it/s]\n 54%|█████▎    | 15/28 [00:07<00:06,  1.87it/s]\n 57%|█████▋    | 16/28 [00:08<00:06,  1.87it/s]\n 61%|██████    | 17/28 [00:08<00:05,  1.87it/s]\n 64%|██████▍   | 18/28 [00:09<00:05,  1.87it/s]\n 68%|██████▊   | 19/28 [00:10<00:04,  1.87it/s]\n 71%|███████▏  | 20/28 [00:10<00:04,  1.87it/s]\n 75%|███████▌  | 21/28 [00:11<00:03,  1.87it/s]\n 79%|███████▊  | 22/28 [00:11<00:03,  1.87it/s]\n 82%|████████▏ | 23/28 [00:12<00:02,  1.87it/s]\n 86%|████████▌ | 24/28 [00:12<00:02,  1.87it/s]\n 89%|████████▉ | 25/28 [00:13<00:01,  1.87it/s]\n 93%|█████████▎| 26/28 [00:13<00:01,  1.87it/s]\n 96%|█████████▋| 27/28 [00:14<00:00,  1.87it/s]\n100%|██████████| 28/28 [00:14<00:00,  1.87it/s]\n100%|██████████| 28/28 [00:14<00:00,  1.89it/s]",
  "output": [
    "https://replicate.delivery/yhqm/dqnmsMdcP5LKHdyB7KwvalxWMk82PP1pBiFSbmkwFaXiaK1E/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-08-20T19:03:19.384Z",
  "started_at": "2024-08-20T19:03:19.393236Z",
  "completed_at": "2024-08-20T19:03:37.858339Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/x71fmj0jb1rj00che4pa5j2xnc/cancel",
    "get": "https://api.replicate.com/v1/predictions/x71fmj0jb1rj00che4pa5j2xnc",
    "web": "https://replicate.com/p/x71fmj0jb1rj00che4pa5j2xnc"
  },
  "metrics": {
    "predict_time": 18.465103505,
    "total_time": 18.474339
  }
}

Generated in

18.5 seconds

Tweak it Report

Using seed: 11405 Prompt: a portrait photo of TOK as a charismatic female speaker giving a TED talk, captured gesturing mid-speech on stage. She has purple hair and is wearing business casual clothes. She's also wearing a simple black lanyard hanging around her neck. The lanyard badge has the text "Replicate" Behind her, there is a presentation with the text "How I made 100k MRR" txt2img mode 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 2024-08-20T19:03:19Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3183c8e9c43647c8 url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar 2024-08-20T19:03:20Z | INFO | [ Complete ] dest=/src/weights-cache/3183c8e9c43647c8 size="172 MB" total_elapsed=1.109s url=https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar b'' Downloaded weights in 1.1337289810180664 seconds The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k mrr "'] 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:14, 1.88it/s] 7%|▋ | 2/28 [00:00<00:11, 2.18it/s] 11%|█ | 3/28 [00:01<00:12, 2.03it/s] 14%|█▍ | 4/28 [00:02<00:12, 1.96it/s] 18%|█▊ | 5/28 [00:02<00:11, 1.93it/s] 21%|██▏ | 6/28 [00:03<00:11, 1.91it/s] 25%|██▌ | 7/28 [00:03<00:11, 1.90it/s] 29%|██▊ | 8/28 [00:04<00:10, 1.89it/s] 32%|███▏ | 9/28 [00:04<00:10, 1.88it/s] 36%|███▌ | 10/28 [00:05<00:09, 1.88it/s] 39%|███▉ | 11/28 [00:05<00:09, 1.88it/s] 43%|████▎ | 12/28 [00:06<00:08, 1.88it/s] 46%|████▋ | 13/28 [00:06<00:08, 1.87it/s] 50%|█████ | 14/28 [00:07<00:07, 1.87it/s] 54%|█████▎ | 15/28 [00:07<00:06, 1.87it/s] 57%|█████▋ | 16/28 [00:08<00:06, 1.87it/s] 61%|██████ | 17/28 [00:08<00:05, 1.87it/s] 64%|██████▍ | 18/28 [00:09<00:05, 1.87it/s] 68%|██████▊ | 19/28 [00:10<00:04, 1.87it/s] 71%|███████▏ | 20/28 [00:10<00:04, 1.87it/s] 75%|███████▌ | 21/28 [00:11<00:03, 1.87it/s] 79%|███████▊ | 22/28 [00:11<00:03, 1.87it/s] 82%|████████▏ | 23/28 [00:12<00:02, 1.87it/s] 86%|████████▌ | 24/28 [00:12<00:02, 1.87it/s] 89%|████████▉ | 25/28 [00:13<00:01, 1.87it/s] 93%|█████████▎| 26/28 [00:13<00:01, 1.87it/s] 96%|█████████▋| 27/28 [00:14<00:00, 1.87it/s] 100%|██████████| 28/28 [00:14<00:00, 1.87it/s] 100%|██████████| 28/28 [00:14<00:00, 1.89it/s]