MiniMax H3 Ref2VA Runtime Subset

Minimal ComfyUI runtime subset for MiniMax H3 reference-to-video inference.

The model files are unmodified copies from Comfy-Org/MiniMax-H3, repackaged into one repository so deployment systems that cache an entire repository do not need to download unrelated model variants.

Included files

  • models/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors
  • models/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
  • models/vae/minimax_h3_video_vae_fp16.safetensors
  • models/vae/minimax_h3_audio_vae_fp32.safetensors

License and source

These weights remain subject to the MiniMax H3 Community License Agreement. See the upstream repository for full model documentation and usage requirements.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PlatypusDevice/minimax-h3-ref2va-runtime

Finetuned
(112)
this model