lucataco
/
musubi-tuner-lora-converter
Convert musubi-tuner LoRA to ComfyUI compatible format
- Public
- 31 runs
-
CPU
- GitHub
Prediction
lucataco/musubi-tuner-lora-converter:c500c52cIDbhxj0k6bw1rgc0cm7948qxqkf4StatusSucceededSourceWebHardwareCPUTotal durationCreatedInput
- lora
- https://huggingface.co/lucataco/hunyuan-musubi-rose-6/resolve/main/lora.safetensors
- hf_token
- ████████████████████
This value was redacted after being sent to the model.
- hub_model_id
- lucataco/hunyuan-musubi-rose-6-comfyui
- target_format
- other
{ "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" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport 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: "[REDACTED]", 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.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport 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": "[REDACTED]", "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 theREPLICATE_API_TOKEN
environment variableexport 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": "[REDACTED]", "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 Cogbrew 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="[REDACTED]"' \ -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": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-musubi-rose-6-comfyui", "target_format": "other" } }' \ http://localhost:5000/predictions
Output
{ "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 in2025-01-06T06:24:27Z | 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
Prediction
lucataco/musubi-tuner-lora-converter:c500c52cID5jgbdtsyxnrge0cm7m1bsx37zmStatusSucceededSourceWebHardwareCPUTotal durationCreatedInput
- lora
- https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors
- hf_token
- ████████████████████
This value was redacted after being sent to the model.
- hub_model_id
- lucataco/hunyuan-lora-melty-3-comfyui
- target_format
- other
{ "lora": "https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors", "hf_token": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-lora-melty-3-comfyui", "target_format": "other" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport 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-lora-melty-3/resolve/main/lora.safetensors", hf_token: "[REDACTED]", hub_model_id: "lucataco/hunyuan-lora-melty-3-comfyui", target_format: "other" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport 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-lora-melty-3/resolve/main/lora.safetensors", "hf_token": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-lora-melty-3-comfyui", "target_format": "other" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport 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-lora-melty-3/resolve/main/lora.safetensors", "hf_token": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-lora-melty-3-comfyui", "target_format": "other" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew 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-lora-melty-3/resolve/main/lora.safetensors"' \ -i 'hf_token="[REDACTED]"' \ -i 'hub_model_id="lucataco/hunyuan-lora-melty-3-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-lora-melty-3/resolve/main/lora.safetensors", "hf_token": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-lora-melty-3-comfyui", "target_format": "other" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2025-01-06T19:06:28.379375Z", "created_at": "2025-01-06T19:05:44.941000Z", "data_removed": false, "error": null, "id": "5jgbdtsyxnrge0cm7m1bsx37zm", "input": { "lora": "https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors", "hf_token": "[REDACTED]", "hub_model_id": "lucataco/hunyuan-lora-melty-3-comfyui", "target_format": "other" }, "logs": "2025-01-06T19:06:07Z | INFO | [ Initiating ] chunk_size=150M dest=lora/lora.safetensors url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors\n2025-01-06T19:06:08Z | INFO | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/21/00/210015dc72e342c28f41e327c891d89801f79b187ea18942c782696c0d941ecb/bd66b7c98536cde3c7468787df9f8f2dd66e49d272f82bd0842097353507a08d?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1736449567&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczNjQ0OTU2N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzIxLzAwLzIxMDAxNWRjNzJlMzQyYzI4ZjQxZTMyN2M4OTFkODk4MDFmNzliMTg3ZWExODk0MmM3ODI2OTZjMGQ5NDFlY2IvYmQ2NmI3Yzk4NTM2Y2RlM2M3NDY4Nzg3ZGY5ZjhmMmRkNjZlNDlkMjcyZjgyYmQwODQyMDk3MzUzNTA3YTA4ZD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=P-dDEKYJpxbMAbVZygEySUZTiMcPTmgvRf8YJlvXeY9rqcMs83ryx95Q3ixJqU08MnwYfT3GvqaCfb7bMZFxdTkiFPNpjpSMH0HqWZo6y8zLWYikulD693TDlYRuabRoEkoqeN5QmXre%7E-e-ICZLse4nyRGJV4OVC9XGjedKzoTB2kq7BCYDyDqvHEqnHrukPowkJhKQh1FgCpBbDhbrg9BwsgjZ2l3qQ8K8fl74EYBjisaYwAtShSf4NgQjSZFWXxL5y5jbxcK0cNbFPFXcY0XW4KofRHS1X-pEvpO4wqeAQwvpPsXvV01QSdBlXeYQSVg9zSAWQz5uXtc7c7-KjQ__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors\n2025-01-06T19:06:12Z | INFO | [ Complete ] dest=lora/lora.safetensors size=\"323 MB\" total_elapsed=4.300s url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/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%| | 131k/323M [00:00<04:27, 1.20MB/s]\nconverted_lora.safetensors: 4%|▍ | 12.9M/323M [00:00<00:04, 72.8MB/s]\nconverted_lora.safetensors: 6%|▋ | 20.4M/323M [00:00<00:05, 50.5MB/s]\nconverted_lora.safetensors: 10%|▉ | 32.0M/323M [00:00<00:06, 41.9MB/s]\nconverted_lora.safetensors: 15%|█▍ | 48.0M/323M [00:00<00:05, 52.3MB/s]\nconverted_lora.safetensors: 20%|█▉ | 64.0M/323M [00:01<00:04, 59.0MB/s]\nconverted_lora.safetensors: 25%|██▍ | 80.0M/323M [00:01<00:05, 47.4MB/s]\nconverted_lora.safetensors: 30%|██▉ | 96.0M/323M [00:01<00:04, 53.0MB/s]\nconverted_lora.safetensors: 35%|███▍ | 112M/323M [00:02<00:03, 54.6MB/s] \nconverted_lora.safetensors: 40%|███▉ | 128M/323M [00:02<00:03, 59.6MB/s]\nconverted_lora.safetensors: 45%|████▍ | 144M/323M [00:02<00:02, 59.6MB/s]\nconverted_lora.safetensors: 48%|████▊ | 155M/323M [00:02<00:02, 65.2MB/s]\nconverted_lora.safetensors: 50%|█████ | 163M/323M [00:02<00:02, 54.3MB/s]\nconverted_lora.safetensors: 55%|█████▍ | 176M/323M [00:03<00:03, 41.1MB/s]\nconverted_lora.safetensors: 60%|█████▉ | 192M/323M [00:03<00:02, 46.7MB/s]\nconverted_lora.safetensors: 64%|██████▍ | 208M/323M [00:03<00:02, 52.2MB/s]\nconverted_lora.safetensors: 69%|██████▉ | 224M/323M [00:04<00:01, 54.1MB/s]\nconverted_lora.safetensors: 74%|███████▍ | 240M/323M [00:04<00:01, 57.4MB/s]\nconverted_lora.safetensors: 79%|███████▉ | 256M/323M [00:04<00:01, 57.1MB/s]\nconverted_lora.safetensors: 84%|████████▍ | 272M/323M [00:04<00:00, 62.4MB/s]\nconverted_lora.safetensors: 89%|████████▉ | 288M/323M [00:05<00:00, 56.4MB/s]\nconverted_lora.safetensors: 94%|█████████▍| 304M/323M [00:05<00:00, 53.5MB/s]\nconverted_lora.safetensors: 99%|█████████▉| 320M/323M [00:06<00:00, 49.1MB/s]\nconverted_lora.safetensors: 100%|██████████| 323M/323M [00:06<00:00, 51.9MB/s]\nhttps://huggingface.co/lucataco/hunyuan-lora-melty-3-comfyui/tree/main/.\n./\n./converted_lora.safetensors", "metrics": { "predict_time": 20.545889502, "total_time": 43.438375 }, "output": "https://replicate.delivery/czjl/30m3naDL5R6HBpwihHsQR0HGGA7u2JCnsa85kKWqhCeZ3OBKA/trained_model.tar", "started_at": "2025-01-06T19:06:07.833485Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/fddq-5mfpklym7qhxyvedzuigqo347ib2y5wtlgm5vr6gsbi6j5vdm3tq", "get": "https://api.replicate.com/v1/predictions/5jgbdtsyxnrge0cm7m1bsx37zm", "cancel": "https://api.replicate.com/v1/predictions/5jgbdtsyxnrge0cm7m1bsx37zm/cancel" }, "version": "c500c52cbc29dbed282623daf0814d361e12c52665554ca984c375a8d1bac153" }
Generated in2025-01-06T19:06:07Z | INFO | [ Initiating ] chunk_size=150M dest=lora/lora.safetensors url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors 2025-01-06T19:06:08Z | INFO | [ Redirect ] redirect_url=https://cdn-lfs-us-1.hf.co/repos/21/00/210015dc72e342c28f41e327c891d89801f79b187ea18942c782696c0d941ecb/bd66b7c98536cde3c7468787df9f8f2dd66e49d272f82bd0842097353507a08d?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27lora.safetensors%3B+filename%3D%22lora.safetensors%22%3B&Expires=1736449567&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczNjQ0OTU2N319LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzIxLzAwLzIxMDAxNWRjNzJlMzQyYzI4ZjQxZTMyN2M4OTFkODk4MDFmNzliMTg3ZWExODk0MmM3ODI2OTZjMGQ5NDFlY2IvYmQ2NmI3Yzk4NTM2Y2RlM2M3NDY4Nzg3ZGY5ZjhmMmRkNjZlNDlkMjcyZjgyYmQwODQyMDk3MzUzNTA3YTA4ZD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSoifV19&Signature=P-dDEKYJpxbMAbVZygEySUZTiMcPTmgvRf8YJlvXeY9rqcMs83ryx95Q3ixJqU08MnwYfT3GvqaCfb7bMZFxdTkiFPNpjpSMH0HqWZo6y8zLWYikulD693TDlYRuabRoEkoqeN5QmXre%7E-e-ICZLse4nyRGJV4OVC9XGjedKzoTB2kq7BCYDyDqvHEqnHrukPowkJhKQh1FgCpBbDhbrg9BwsgjZ2l3qQ8K8fl74EYBjisaYwAtShSf4NgQjSZFWXxL5y5jbxcK0cNbFPFXcY0XW4KofRHS1X-pEvpO4wqeAQwvpPsXvV01QSdBlXeYQSVg9zSAWQz5uXtc7c7-KjQ__&Key-Pair-Id=K24J24Z295AEI9 url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/resolve/main/lora.safetensors 2025-01-06T19:06:12Z | INFO | [ Complete ] dest=lora/lora.safetensors size="323 MB" total_elapsed=4.300s url=https://huggingface.co/lucataco/hunyuan-lora-melty-3/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%| | 131k/323M [00:00<04:27, 1.20MB/s] converted_lora.safetensors: 4%|▍ | 12.9M/323M [00:00<00:04, 72.8MB/s] converted_lora.safetensors: 6%|▋ | 20.4M/323M [00:00<00:05, 50.5MB/s] converted_lora.safetensors: 10%|▉ | 32.0M/323M [00:00<00:06, 41.9MB/s] converted_lora.safetensors: 15%|█▍ | 48.0M/323M [00:00<00:05, 52.3MB/s] converted_lora.safetensors: 20%|█▉ | 64.0M/323M [00:01<00:04, 59.0MB/s] converted_lora.safetensors: 25%|██▍ | 80.0M/323M [00:01<00:05, 47.4MB/s] converted_lora.safetensors: 30%|██▉ | 96.0M/323M [00:01<00:04, 53.0MB/s] converted_lora.safetensors: 35%|███▍ | 112M/323M [00:02<00:03, 54.6MB/s] converted_lora.safetensors: 40%|███▉ | 128M/323M [00:02<00:03, 59.6MB/s] converted_lora.safetensors: 45%|████▍ | 144M/323M [00:02<00:02, 59.6MB/s] converted_lora.safetensors: 48%|████▊ | 155M/323M [00:02<00:02, 65.2MB/s] converted_lora.safetensors: 50%|█████ | 163M/323M [00:02<00:02, 54.3MB/s] converted_lora.safetensors: 55%|█████▍ | 176M/323M [00:03<00:03, 41.1MB/s] converted_lora.safetensors: 60%|█████▉ | 192M/323M [00:03<00:02, 46.7MB/s] converted_lora.safetensors: 64%|██████▍ | 208M/323M [00:03<00:02, 52.2MB/s] converted_lora.safetensors: 69%|██████▉ | 224M/323M [00:04<00:01, 54.1MB/s] converted_lora.safetensors: 74%|███████▍ | 240M/323M [00:04<00:01, 57.4MB/s] converted_lora.safetensors: 79%|███████▉ | 256M/323M [00:04<00:01, 57.1MB/s] converted_lora.safetensors: 84%|████████▍ | 272M/323M [00:04<00:00, 62.4MB/s] converted_lora.safetensors: 89%|████████▉ | 288M/323M [00:05<00:00, 56.4MB/s] converted_lora.safetensors: 94%|█████████▍| 304M/323M [00:05<00:00, 53.5MB/s] converted_lora.safetensors: 99%|█████████▉| 320M/323M [00:06<00:00, 49.1MB/s] converted_lora.safetensors: 100%|██████████| 323M/323M [00:06<00:00, 51.9MB/s] https://huggingface.co/lucataco/hunyuan-lora-melty-3-comfyui/tree/main/. ./ ./converted_lora.safetensors
Want to make some of these yourself?
Run this model