Prediction

Model

lucataco/flux-dev-multi-lora:3de6b583

bfw21g1b8drj00chcfp8w5hb20

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

25.0s

Created

over 1 year ago by lucataco

Webhook

–

Input

prompt: a photo of TOK, sftsrv style
aspect_ratio: 1:1
num_outputs: 1
num_inference_steps: 28
guidance_scale: 3.5
output_format: png
output_quality: 80
hf_loras: https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar, alvdansen/softserve_anime

{
  "aspect_ratio": "1:1",
  "guidance_scale": 3.5,
  "hf_loras": [
    "https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar",
    "alvdansen/softserve_anime"
  ],
  "num_inference_steps": 28,
  "num_outputs": 1,
  "output_format": "png",
  "output_quality": 80,
  "prompt": "a photo of TOK, sftsrv style"
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Qqo**********************************

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-multi-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-multi-lora:3de6b583ede26d67e96fe222b68fd249545e38509a66a3feee435ae961b4b842",
  {
    input: {
      aspect_ratio: "1:1",
      guidance_scale: 3.5,
      hf_loras: ["https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar","alvdansen/softserve_anime"],
      num_inference_steps: 28,
      num_outputs: 1,
      output_format: "png",
      output_quality: 80,
      prompt: "a photo of TOK, sftsrv style"
    }
  }
);

// 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_Qqo**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

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

output = replicate.run(
    "lucataco/flux-dev-multi-lora:3de6b583ede26d67e96fe222b68fd249545e38509a66a3feee435ae961b4b842",
    input={
        "aspect_ratio": "1:1",
        "guidance_scale": 3.5,
        "hf_loras": ["https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar","alvdansen/softserve_anime"],
        "num_inference_steps": 28,
        "num_outputs": 1,
        "output_format": "png",
        "output_quality": 80,
        "prompt": "a photo of TOK, sftsrv style"
    }
)

# 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_Qqo**********************************

This is your API token. Keep it to yourself.

Run lucataco/flux-dev-multi-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-multi-lora:3de6b583ede26d67e96fe222b68fd249545e38509a66a3feee435ae961b4b842",
    "input": {
      "aspect_ratio": "1:1",
      "guidance_scale": 3.5,
      "hf_loras": ["https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar","alvdansen/softserve_anime"],
      "num_inference_steps": 28,
      "num_outputs": 1,
      "output_format": "png",
      "output_quality": 80,
      "prompt": "a photo of TOK, sftsrv style"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "bfw21g1b8drj00chcfp8w5hb20",
  "model": "lucataco/flux-dev-multi-lora",
  "version": "3de6b583ede26d67e96fe222b68fd249545e38509a66a3feee435ae961b4b842",
  "input": {
    "aspect_ratio": "1:1",
    "guidance_scale": 3.5,
    "hf_loras": [
      "https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar",
      "alvdansen/softserve_anime"
    ],
    "num_inference_steps": 28,
    "num_outputs": 1,
    "output_format": "png",
    "output_quality": 80,
    "prompt": "a photo of TOK, sftsrv style"
  },
  "logs": "Using seed: 24558\nPrompt: a photo of TOK, sftsrv style\ntxt2img mode\nDownloading LoRA weights from - Replicate URL: https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar\nDownloading LoRA weights from - HF path: alvdansen/softserve_anime\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:15,  1.69it/s]\n  7%|▋         | 2/28 [00:01<00:13,  1.90it/s]\n 11%|█         | 3/28 [00:01<00:13,  1.80it/s]\n 14%|█▍        | 4/28 [00:02<00:13,  1.75it/s]\n 18%|█▊        | 5/28 [00:02<00:13,  1.73it/s]\n 21%|██▏       | 6/28 [00:03<00:12,  1.71it/s]\n 25%|██▌       | 7/28 [00:04<00:12,  1.71it/s]\n 29%|██▊       | 8/28 [00:04<00:11,  1.70it/s]\n 32%|███▏      | 9/28 [00:05<00:11,  1.70it/s]\n 36%|███▌      | 10/28 [00:05<00:10,  1.69it/s]\n 39%|███▉      | 11/28 [00:06<00:10,  1.69it/s]\n 43%|████▎     | 12/28 [00:07<00:09,  1.69it/s]\n 46%|████▋     | 13/28 [00:07<00:08,  1.69it/s]\n 50%|█████     | 14/28 [00:08<00:08,  1.68it/s]\n 54%|█████▎    | 15/28 [00:08<00:07,  1.68it/s]\n 57%|█████▋    | 16/28 [00:09<00:07,  1.68it/s]\n 61%|██████    | 17/28 [00:09<00:06,  1.68it/s]\n 64%|██████▍   | 18/28 [00:10<00:05,  1.68it/s]\n 68%|██████▊   | 19/28 [00:11<00:05,  1.68it/s]\n 71%|███████▏  | 20/28 [00:11<00:04,  1.68it/s]\n 75%|███████▌  | 21/28 [00:12<00:04,  1.68it/s]\n 79%|███████▊  | 22/28 [00:12<00:03,  1.68it/s]\n 82%|████████▏ | 23/28 [00:13<00:02,  1.68it/s]\n 86%|████████▌ | 24/28 [00:14<00:02,  1.68it/s]\n 89%|████████▉ | 25/28 [00:14<00:01,  1.68it/s]\n 93%|█████████▎| 26/28 [00:15<00:01,  1.68it/s]\n 96%|█████████▋| 27/28 [00:15<00:00,  1.68it/s]\n100%|██████████| 28/28 [00:16<00:00,  1.68it/s]\n100%|██████████| 28/28 [00:16<00:00,  1.70it/s]",
  "output": [
    "https://replicate.delivery/yhqm/pPlEXdkJlV4CPRgf5TXUDVSJeVZdaeTcA8iv8bQf9qUsjNPNB/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-08-18T05:18:27.651Z",
  "started_at": "2024-08-18T05:18:27.660244Z",
  "completed_at": "2024-08-18T05:18:52.636088Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/bfw21g1b8drj00chcfp8w5hb20/cancel",
    "get": "https://api.replicate.com/v1/predictions/bfw21g1b8drj00chcfp8w5hb20",
    "web": "https://replicate.com/p/bfw21g1b8drj00chcfp8w5hb20"
  },
  "metrics": {
    "predict_time": 24.975843841,
    "total_time": 24.985088
  }
}

Generated in

25.0 seconds

Tweak it Report

Using seed: 24558 Prompt: a photo of TOK, sftsrv style txt2img mode Downloading LoRA weights from - Replicate URL: https://replicate.delivery/yhqm/xIUPCppeslXbaC6D8hzONTPKFURik2zRMLmmif0GRq2f55lmA/trained_model.tar Downloading LoRA weights from - HF path: alvdansen/softserve_anime 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:15, 1.69it/s] 7%|▋ | 2/28 [00:01<00:13, 1.90it/s] 11%|█ | 3/28 [00:01<00:13, 1.80it/s] 14%|█▍ | 4/28 [00:02<00:13, 1.75it/s] 18%|█▊ | 5/28 [00:02<00:13, 1.73it/s] 21%|██▏ | 6/28 [00:03<00:12, 1.71it/s] 25%|██▌ | 7/28 [00:04<00:12, 1.71it/s] 29%|██▊ | 8/28 [00:04<00:11, 1.70it/s] 32%|███▏ | 9/28 [00:05<00:11, 1.70it/s] 36%|███▌ | 10/28 [00:05<00:10, 1.69it/s] 39%|███▉ | 11/28 [00:06<00:10, 1.69it/s] 43%|████▎ | 12/28 [00:07<00:09, 1.69it/s] 46%|████▋ | 13/28 [00:07<00:08, 1.69it/s] 50%|█████ | 14/28 [00:08<00:08, 1.68it/s] 54%|█████▎ | 15/28 [00:08<00:07, 1.68it/s] 57%|█████▋ | 16/28 [00:09<00:07, 1.68it/s] 61%|██████ | 17/28 [00:09<00:06, 1.68it/s] 64%|██████▍ | 18/28 [00:10<00:05, 1.68it/s] 68%|██████▊ | 19/28 [00:11<00:05, 1.68it/s] 71%|███████▏ | 20/28 [00:11<00:04, 1.68it/s] 75%|███████▌ | 21/28 [00:12<00:04, 1.68it/s] 79%|███████▊ | 22/28 [00:12<00:03, 1.68it/s] 82%|████████▏ | 23/28 [00:13<00:02, 1.68it/s] 86%|████████▌ | 24/28 [00:14<00:02, 1.68it/s] 89%|████████▉ | 25/28 [00:14<00:01, 1.68it/s] 93%|█████████▎| 26/28 [00:15<00:01, 1.68it/s] 96%|█████████▋| 27/28 [00:15<00:00, 1.68it/s] 100%|██████████| 28/28 [00:16<00:00, 1.68it/s] 100%|██████████| 28/28 [00:16<00:00, 1.70it/s]