lucataco/musubi-tuner-lora-converter:c500c52c – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

lucataco /musubi-tuner-lora-converter:c500c52c

Playground API

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=lucataco/musubi-tuner-lora-converter

or set up a project from scratch

Install Replicate’s Node.js client library

npm install replicate

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "lucataco/musubi-tuner-lora-converter:c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153",
  {
    input: {
      lora: "https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors",
      hf_token: "",
      hub_model_id: "lucataco/hunyuan-musubi-rose-6-comfyui",
      target_format: "other"
    }
  }
);
console.log(output);

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=<paste-your-token-here>

Find your API token in your account settings.

Import the client

import replicate

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

output = replicate.run(
    "lucataco/musubi-tuner-lora-converter:c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153",
    input={
        "lora": "https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors",
        "hf_token": "",
        "hub_model_id": "lucataco/hunyuan-musubi-rose-6-comfyui",
        "target_format": "other"
    }
)
print(output)

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=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/musubi-tuner-lora-converter 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": "c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153",
    "input": {
      "lora": "https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors",
      "hf_token": "",
      "hub_model_id": "lucataco/hunyuan-musubi-rose-6-comfyui",
      "target_format": "other"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run lucataco/musubi-tuner-lora-converter using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/lucataco/musubi-tuner-lora-converter@sha256:c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153 \
  -i 'lora="https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors"' \
  -i 'hf_token=""' \
  -i 'hub_model_id="lucataco/hunyuan-musubi-rose-6-comfyui"' \
  -i 'target_format="other"'

To learn more, take a look at the Cog documentation.

Pull and run lucataco/musubi-tuner-lora-converter using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 r8.im/lucataco/musubi-tuner-lora-converter@sha256:c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "lora": "https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors",
      "hf_token": "",
      "hub_model_id": "lucataco/hunyuan-musubi-rose-6-comfyui",
      "target_format": "other"
    }
  }' \
  http://localhost:5000/predictions

Output

trained_model.tar

{
  "completed_at": "2025-01-06T06:24:49.008991Z",
  "created_at": "2025-01-06T06:23:56.896000Z",
  "data_removed": false,
  "error": null,
  "id": "bhxj0k6bw1rgc0cm7948qxqkf4",
  "input": {
    "lora": "https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors",
    "hf_token": "[REDACTED]",
    "hub_model_id": "lucataco/hunyuan-musubi-rose-6-comfyui",
    "target_format": "other"
  },
  "logs": "2025-01-06T06:24:27Z | INFO  | [ Initiating ] chunk_size=150M dest=lora/lora.safetensors url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors\n2025-01-06T06:24:27Z | INFO  | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/c9/46/c946b54c775d95b53a3cdd5709ddbc10fc6150adbea2f1cad6ea2f48b22c2c52/9d7cb11a7126f633023cf0d375033c279793aa1c0e96cb536d2e09e42f13b7ab?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1736403867&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczNjQwMzg2N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zL2M5LzQ2L2M5NDZiNTRjNzc1ZDk1YjUzYTNjZGQ1NzA5ZGRiYzEwZmM2MTUwYWRiZWEyZjFjYWQ2ZWEyZjQ4YjIyYzJjNTIvOWQ3Y2IxMWE3MTI2ZjYzMzAyM2NmMGQzNzUwMzNjMjc5NzkzYWExYzBlOTZjYjUzNmQyZTA5ZTQyZjEzYjdhYj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=G%7EyFGOZ8vjmOl5jmSar7ZFo5fpM5uKibgJEor0YvKvp5hkhEd%7EJJZxdyaKgJjb%7E2iuIVcuxV5lOAWeJIvGBGpfGroLcJPCafzp0mM-1mSbdGMQC421Tu4sMD6XWTpbjMXa3BZqgEOYvmFY9cM1rAlPtRK1-UX9TFQWlooGgQTSlqCyTDzVk9G9H-D4C0MuRKYiDN4c%7E-T3YEyWb-aYItTMaJ0YOvD-MY74s6%7EQGi1qD42c7lxurqytNWnnl6DfSKiIo1GIdh7ebTf9lGh06mJA0dXa%7EbWJx4nzUkhsmnueRGW8HJou4qUIzdw8OlmPdykODzpFz9GgUJfT1zkfH6tQ__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors\n2025-01-06T06:24:31Z | INFO  | [ Complete ] dest=lora/lora.safetensors size=\"323 MB\" total_elapsed=4.456s url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors\nConverting LoRA to target format: other\nINFO:__main__:loading lora/lora.safetensors\nINFO:__main__:converting to other\nINFO:__main__:saving to output/converted_lora.safetensors\nINFO:__main__:done\nThe token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\nToken is valid (permission: write).\nThe token `Discord` has been saved to /root/.cache/huggingface/stored_tokens\nYour token has been saved to /root/.cache/huggingface/token\nLogin successful.\nThe current active token is: `Discord`\nConsider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.\nStart hashing 1 files.\nFinished hashing 1 files.\nconverted_lora.safetensors:   0%|          | 0.00/323M [00:00<?, ?B/s]\nconverted_lora.safetensors:   0%|          | 16.4k/323M [00:00<37:33, 143kB/s]\nconverted_lora.safetensors:   2%|▏         | 7.31M/323M [00:00<00:08, 38.3MB/s]\nconverted_lora.safetensors:   5%|▍         | 16.0M/323M [00:00<00:08, 35.9MB/s]\nconverted_lora.safetensors:   9%|▊         | 27.5M/323M [00:00<00:05, 55.2MB/s]\nconverted_lora.safetensors:  10%|█         | 33.7M/323M [00:00<00:08, 34.9MB/s]\nconverted_lora.safetensors:  13%|█▎        | 43.5M/323M [00:01<00:05, 46.6MB/s]\nconverted_lora.safetensors:  15%|█▌        | 49.8M/323M [00:01<00:07, 38.3MB/s]\nconverted_lora.safetensors:  19%|█▉        | 61.7M/323M [00:01<00:04, 53.7MB/s]\nconverted_lora.safetensors:  21%|██▏       | 68.9M/323M [00:01<00:05, 44.3MB/s]\nconverted_lora.safetensors:  25%|██▍       | 80.0M/323M [00:01<00:04, 48.6MB/s]\nconverted_lora.safetensors:  28%|██▊       | 91.5M/323M [00:01<00:03, 58.9MB/s]\nconverted_lora.safetensors:  31%|███       | 98.5M/323M [00:02<00:05, 43.9MB/s]\nconverted_lora.safetensors:  33%|███▎      | 107M/323M [00:02<00:04, 51.5MB/s] \nconverted_lora.safetensors:  35%|███▌      | 114M/323M [00:02<00:05, 41.0MB/s]\nconverted_lora.safetensors:  39%|███▉      | 126M/323M [00:02<00:03, 52.6MB/s]\nconverted_lora.safetensors:  41%|████      | 132M/323M [00:02<00:04, 43.1MB/s]\nconverted_lora.safetensors:  44%|████▍     | 143M/323M [00:03<00:03, 53.7MB/s]\nconverted_lora.safetensors:  46%|████▋     | 150M/323M [00:03<00:05, 33.5MB/s]\nconverted_lora.safetensors:  49%|████▉     | 158M/323M [00:03<00:04, 39.8MB/s]\nconverted_lora.safetensors:  51%|█████     | 163M/323M [00:03<00:04, 33.4MB/s]\nconverted_lora.safetensors:  55%|█████▍    | 176M/323M [00:04<00:03, 39.6MB/s]\nconverted_lora.safetensors:  60%|█████▉    | 192M/323M [00:04<00:02, 45.5MB/s]\nconverted_lora.safetensors:  64%|██████▎   | 205M/323M [00:04<00:02, 58.0MB/s]\nconverted_lora.safetensors:  66%|██████▌   | 212M/323M [00:04<00:02, 47.6MB/s]\nconverted_lora.safetensors:  69%|██████▉   | 224M/323M [00:05<00:02, 35.0MB/s]\nconverted_lora.safetensors:  74%|███████▍  | 240M/323M [00:05<00:01, 42.6MB/s]\nconverted_lora.safetensors:  79%|███████▉  | 256M/323M [00:05<00:01, 47.9MB/s]\nconverted_lora.safetensors:  83%|████████▎ | 269M/323M [00:05<00:00, 57.1MB/s]\nconverted_lora.safetensors:  86%|████████▌ | 276M/323M [00:06<00:00, 47.9MB/s]\nconverted_lora.safetensors:  89%|████████▉ | 288M/323M [00:06<00:00, 49.0MB/s]\nconverted_lora.safetensors:  94%|█████████▍| 304M/323M [00:06<00:00, 53.5MB/s]\nconverted_lora.safetensors:  99%|█████████▉| 320M/323M [00:06<00:00, 60.6MB/s]\nconverted_lora.safetensors: 100%|██████████| 323M/323M [00:06<00:00, 46.2MB/s]\nhttps://huggingface.co/lucataco/hunyuan-musubi-rose-6-comfyui/tree/main/.\n./\n./converted_lora.safetensors",
  "metrics": {
    "predict_time": 22.870439322,
    "total_time": 52.112991
  },
  "output": "https://replicate.delivery/czjl/hawefYIJF6vQ60EGgrui4OPefUKqMwBB28RGScJrV9K9SKJQB/trained_model.tar",
  "started_at": "2025-01-06T06:24:26.138551Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/fddq-tcepnnh7s3v5qrokddqjwwpwgcgk2dsmhwhk5z5cjzlfadliaq2a",
    "get": "https://api.replicate.com/v1/predictions/bhxj0k6bw1rgc0cm7948qxqkf4",
    "cancel": "https://api.replicate.com/v1/predictions/bhxj0k6bw1rgc0cm7948qxqkf4/cancel"
  },
  "version": "c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153"
}

Generated in

22.9 seconds

Tweak it ShareReport

2025-01-06T06:24:27Z | INFO  | [ Initiating ] chunk_size=150M dest=lora/lora.safetensors url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors
2025-01-06T06:24:27Z | INFO  | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/c9/46/c946b54c775d95b53a3cdd5709ddbc10fc6150adbea2f1cad6ea2f48b22c2c52/9d7cb11a7126f633023cf0d375033c279793aa1c0e96cb536d2e09e42f13b7ab?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1736403867&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczNjQwMzg2N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zL2M5LzQ2L2M5NDZiNTRjNzc1ZDk1YjUzYTNjZGQ1NzA5ZGRiYzEwZmM2MTUwYWRiZWEyZjFjYWQ2ZWEyZjQ4YjIyYzJjNTIvOWQ3Y2IxMWE3MTI2ZjYzMzAyM2NmMGQzNzUwMzNjMjc5NzkzYWExYzBlOTZjYjUzNmQyZTA5ZTQyZjEzYjdhYj9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=G%7EyFGOZ8vjmOl5jmSar7ZFo5fpM5uKibgJEor0YvKvp5hkhEd%7EJJZxdyaKgJjb%7E2iuIVcuxV5lOAWeJIvGBGpfGroLcJPCafzp0mM-1mSbdGMQC421Tu4sMD6XWTpbjMXa3BZqgEOYvmFY9cM1rAlPtRK1-UX9TFQWlooGgQTSlqCyTDzVk9G9H-D4C0MuRKYiDN4c%7E-T3YEyWb-aYItTMaJ0YOvD-MY74s6%7EQGi1qD42c7lxurqytNWnnl6DfSKiIo1GIdh7ebTf9lGh06mJA0dXa%7EbWJx4nzUkhsmnueRGW8HJou4qUIzdw8OlmPdykODzpFz9GgUJfT1zkfH6tQ__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors
2025-01-06T06:24:31Z | INFO  | [ Complete ] dest=lora/lora.safetensors size="323 MB" total_elapsed=4.456s url=https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors
Converting LoRA to target format: other
INFO:__main__:loading lora/lora.safetensors
INFO:__main__:converting to other
INFO:__main__:saving to output/converted_lora.safetensors
INFO:__main__:done
The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: write).
The token `Discord` has been saved to /root/.cache/huggingface/stored_tokens
Your token has been saved to /root/.cache/huggingface/token
Login successful.
The current active token is: `Discord`
Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.
Start hashing 1 files.
Finished hashing 1 files.
converted_lora.safetensors:   0%|          | 0.00/323M [00:00<?, ?B/s]
converted_lora.safetensors:   0%|          | 16.4k/323M [00:00<37:33, 143kB/s]
converted_lora.safetensors:   2%|▏         | 7.31M/323M [00:00<00:08, 38.3MB/s]
converted_lora.safetensors:   5%|▍         | 16.0M/323M [00:00<00:08, 35.9MB/s]
converted_lora.safetensors:   9%|▊         | 27.5M/323M [00:00<00:05, 55.2MB/s]
converted_lora.safetensors:  10%|█         | 33.7M/323M [00:00<00:08, 34.9MB/s]
converted_lora.safetensors:  13%|█▎        | 43.5M/323M [00:01<00:05, 46.6MB/s]
converted_lora.safetensors:  15%|█▌        | 49.8M/323M [00:01<00:07, 38.3MB/s]
converted_lora.safetensors:  19%|█▉        | 61.7M/323M [00:01<00:04, 53.7MB/s]
converted_lora.safetensors:  21%|██▏       | 68.9M/323M [00:01<00:05, 44.3MB/s]
converted_lora.safetensors:  25%|██▍       | 80.0M/323M [00:01<00:04, 48.6MB/s]
converted_lora.safetensors:  28%|██▊       | 91.5M/323M [00:01<00:03, 58.9MB/s]
converted_lora.safetensors:  31%|███       | 98.5M/323M [00:02<00:05, 43.9MB/s]
converted_lora.safetensors:  33%|███▎      | 107M/323M [00:02<00:04, 51.5MB/s] 
converted_lora.safetensors:  35%|███▌      | 114M/323M [00:02<00:05, 41.0MB/s]
converted_lora.safetensors:  39%|███▉      | 126M/323M [00:02<00:03, 52.6MB/s]
converted_lora.safetensors:  41%|████      | 132M/323M [00:02<00:04, 43.1MB/s]
converted_lora.safetensors:  44%|████▍     | 143M/323M [00:03<00:03, 53.7MB/s]
converted_lora.safetensors:  46%|████▋     | 150M/323M [00:03<00:05, 33.5MB/s]
converted_lora.safetensors:  49%|████▉     | 158M/323M [00:03<00:04, 39.8MB/s]
converted_lora.safetensors:  51%|█████     | 163M/323M [00:03<00:04, 33.4MB/s]
converted_lora.safetensors:  55%|█████▍    | 176M/323M [00:04<00:03, 39.6MB/s]
converted_lora.safetensors:  60%|█████▉    | 192M/323M [00:04<00:02, 45.5MB/s]
converted_lora.safetensors:  64%|██████▎   | 205M/323M [00:04<00:02, 58.0MB/s]
converted_lora.safetensors:  66%|██████▌   | 212M/323M [00:04<00:02, 47.6MB/s]
converted_lora.safetensors:  69%|██████▉   | 224M/323M [00:05<00:02, 35.0MB/s]
converted_lora.safetensors:  74%|███████▍  | 240M/323M [00:05<00:01, 42.6MB/s]
converted_lora.safetensors:  79%|███████▉  | 256M/323M [00:05<00:01, 47.9MB/s]
converted_lora.safetensors:  83%|████████▎ | 269M/323M [00:05<00:00, 57.1MB/s]
converted_lora.safetensors:  86%|████████▌ | 276M/323M [00:06<00:00, 47.9MB/s]
converted_lora.safetensors:  89%|████████▉ | 288M/323M [00:06<00:00, 49.0MB/s]
converted_lora.safetensors:  94%|█████████▍| 304M/323M [00:06<00:00, 53.5MB/s]
converted_lora.safetensors:  99%|█████████▉| 320M/323M [00:06<00:00, 60.6MB/s]
converted_lora.safetensors: 100%|██████████| 323M/323M [00:06<00:00, 46.2MB/s]
https://huggingface.co/lucataco/hunyuan-musubi-rose-6-comfyui/tree/main/.
./
./converted_lora.safetensors