Downloads · 30 days
0
minimax-h3-ref2va-runtime
PlatypusDevice/minimax-h3-ref2va-runtime
minimax-h3-ref2va-runtime is a image-to-video model from PlatypusDevice. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Minimal ComfyUI runtime subset for MiniMax H3 reference-to-video inference.
Access
Public
Updated Aug 31, 2026
Repo size
42.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors42.5 GB · 100%
At a glance
- Task
- Image-to-Video
- License
- other
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 31, 2026
- SHA
- 7d3266df
Base models
Model card
From the Hugging Face model README
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.
- Task
- Image-to-Video
- License
- other
- Created
- Aug 29, 2026
- Updated
- Aug 31, 2026