Instructions to use Comfy-Org/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/MiniMax-H3 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
39-second single takes on a 12 GB card with these files
#75
by LIOSAM007 - opened
We run the H3 Remix checkpoint with the text encoder qwen3vl_32b_minimax_h3_nvfp4_awq and the int8 video VAE from this repo on an RTX 4070 SUPER 12 GB with 96 GB RAM, through FeiHou Easy H3 (two passes, 416p upscaled to 624p). Segment 1 takes about 1.5 minutes. Every continued segment takes 2.5-3.5 minutes. Chaining 8 segments by latent tail gives one continuous 39-second shot with no visible seams. Both videos, the graphs and a link to the full method: https://civitai.com/models/3038677