Spaces:
Running on Zero
Download README.md from hugging-apps/mpeg-diffusion: direct link, hf CLI and curl.
- Browser
- Download file 2.76 kB
-
https://huggingface.co/spaces/hugging-apps/mpeg-diffusion/resolve/main/README.md
- Command line
-
hf download hf://spaces/hugging-apps/mpeg-diffusion/README.md
-
curl -L -o README.md https://huggingface.co/spaces/hugging-apps/mpeg-diffusion/resolve/main/README.md
title: MPEG-Diffusion
emoji: ποΈ
colorFrom: purple
colorTo: green
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
python_version: '3.12'
startup_duration_timeout: 1h
short_description: Mixed-resolution text-to-video with a self-selected region
models:
- johndpope/MiniMax-H3-MPEG-Diffusion
MPEG-Diffusion: Mixed-Resolution Video Generation
Text-to-video demo for MPEG-Diffusion (Menn et al.) β a model that generates video the way video codecs think about it:
- a low-resolution track denoises the whole frame cheaply,
- a tiny linear region head self-selects the region that deserves detail,
- a high-resolution track refines only that region through dual-resolution attention,
- the two tracks merge in pixel space β full-res detail where it matters, at roughly half the compute of rendering everything at high resolution.
This Space runs the paper's MiniMax-H3 port
(Apache-2.0, vendored under lot/ + third_party/) with the published research weights from
johndpope/MiniMax-H3-MPEG-Diffusion:
the ridge-fitted KV up-maps and the v3 region head applied to the int8 ConvRot base DiT
(Comfy-Org/MiniMax-H3), at the port's
quality preset β 20 steps, the region chosen at step 16, 6 high-resolution steps, pixel-space
merge, on a short reference-length clip. By default the model picks its own detail region; a
manual box can be forced under Advanced.
Because the 62 GiB Qwen3-VL text encoder does not fit beside the transformer on one GPU, prompt conditioning runs on the qwen3vl-conditioner Space and this Space runs the sampler.
Credits
- Paper: MPEG-Diffusion: Mixed-Resolution Video Generation β Menn et al., arXiv 2611.12069.
- Code: the paper's MiniMax-H3 port, scrya-com/mpeg-diffusion (Apache-2.0).
- Weights: johndpope/MiniMax-H3-MPEG-Diffusion β fitted up-maps + region head on the int8 ConvRot base.
- Base model: MiniMax-H3, subject to the MiniMax H3 Community License β outputs are machine-generated and must be disclosed as such; the license does not permit use in the EU, UK, Republic of Korea or USA, and commercial use by companies above US$20M annual revenue needs written authorization from MiniMax.
- Example prompts: portrait descriptions in the style of Pexels image alt-texts (Pexels content is free to use).