Downloads · 30 days
0
FX-FeiHou/MiniMax-H3-Remix
MiniMax-H3-Remix is a image-to-video model from FX-FeiHou. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for comfyui. The card lists the license as other.
MiniMax-H3 Remix is a custom dual-model H3 remix checkpoint built for ComfyUI video generation.
Downloads · 30 days
0
Access
Public
Updated Aug 25, 2026
Repo size
100 GB
Likes
28
Public
Click a slice to open those files.
.safetensors100 GB · 100%
From the Hugging Face model README
MiniMax-H3 Remix is a custom dual-model H3 remix checkpoint built for ComfyUI video generation.
It uses a hierarchical recombination workflow instead of naive weight averaging: the two H3 branches are reorganized at targeted response blocks, with key modulation layers such as AdaLN handled separately. The goal is to retain stable generation behavior while introducing stronger visual detail, dynamic expression, and refined stylistic response.
LoRA contributions used during remix creation are statically fused into the checkpoint. No corresponding external style LoRAs are required for normal inference.
| Variant | File | Purpose |
|---|---|---|
| BF16 | FeiHou_MiniMax-H3_Remix_v0.6.safetensors | Full-precision, quality-first release |
| INT8 ConvRot | FeiHou_MiniMax-H3_Remix_v0.6_int8_convrot_v2.safetensors | ComfyUI-native low-VRAM deployment |
The INT8 ConvRot version is a quantized deployment variant of the same Remix design. For maximum fidelity, use BF16 when hardware allows.
Place the .safetensors file in:
ComfyUI/models/diffusion_models/
Load it with ComfyUI-FeiHou-Easy-H3.
Use a MiniMax H3-compatible workflow.
res_multistepsimple8-120.75These are starting points rather than fixed requirements. Adjust according to resolution, motion intensity, reference-image strength, and your intended visual style.