Instructions to use kabachuha/ReDiverse-MiniMax-H3-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use kabachuha/ReDiverse-MiniMax-H3-Comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
ComfyUI-compatible conversion of the https://huggingface.co/ReDiverse/ReDiverse-MiniMax-H3 LoRA.
This LoRA is applied on top of the lightx2v (Comfy-supplied) 4-step distilled adapter for MiniMax-H3 with the goal of restoring the generation diversity after distillation.
The first-step activation workflow, then regular sampling (total 4 steps) is located at H3-ReDiverse-Comfy-4steps.json in the root folder.
- Downloads last month
- 127
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for kabachuha/ReDiverse-MiniMax-H3-Comfy
Base model
lightx2v/Minimax-h3-Turbo Adapter
ReDiverse/ReDiverse-MiniMax-H3