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.safetensorsmodels/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensorsmodels/vae/minimax_h3_video_vae_fp16.safetensorsmodels/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.
Model tree for PlatypusDevice/minimax-h3-ref2va-runtime
Base model
MiniMaxAI/MiniMax-H3