Downloads · 30 days
60
50% of all-time downloads
RHC-H3V2
lokitsar/RHC-H3V2
RHC-H3V2 is a machine learning model from lokitsar. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for minimax-h3.
A MiniMax H3 LoRA for simulated clothing-removal transformations in video.
All-time downloads
121
Public
Repo size
155 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors155 MB · 100%
At a glance
- Library
- minimax-h3
- Access
- Public
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026
- SHA
- 5348d74d
Model card
From the Hugging Face model README
RHC-H3V2
A MiniMax H3 LoRA for simulated clothing-removal transformations in video.
Use only with consenting adults or fully synthetic subjects. Do not use it to create sexualized content involving minors or real people without their explicit consent.
Required custom node
This LoRA requires ComfyUI-AIToolkit-MiniMaxH3. The node provides ai-toolkit-compatible reference-video preprocessing so LoRAs trained with ai-toolkit behave correctly in ComfyUI.
Install the custom node in your ComfyUI custom_nodes directory and restart ComfyUI. The node repository also includes an example_workflow.json file.
Usage
- Download
RHC-H3V2_000002000.safetensorsintoComfyUI/models/loras/. - Load the example workflow from the required node repository.
- Add a
LoraLoaderModelOnlynode between the UNET loader andModelSamplingMiniMaxH3. - Select this LoRA in
LoraLoaderModelOnlyand adjust its strength for your workflow.
See the required node documentation for reference-video wiring and recommended workflow settings.
Files
RHC-H3V2_000002000.safetensors— LoRA checkpoint at training step 2000.
- Library
- minimax-h3
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026