Skip to page content
SAVRN
Search Plan a project

Open-weight model

FastH3-8step-V2-overlay

by Kevin Mi kevin-mi/FastH3-8step-V2-overlay

FastH3-8step-V2-overlay is an open-weight model from Kevin Mi. Its published files total 12.8 KB.

Overlay metadata repo for using FastVideo/FastVideo-FastH3-8-Step-V2 with native SGLang Diffusion MiniMax-H3 support. This repo contains only overlay metadata and materialization logic.

Parameters—
Context—
Weights12.8 KB
License—
AccessOpen weights
Monthly Downloads—

Model Card

Overlay metadata repo for using FastVideo/FastVideo-FastH3-8-Step-V2 with native SGLang Diffusion MiniMax-H3 support. This repo contains only overlay metadata and materialization logic. Source weights remain in FastVideo/FastVideo-FastH3-8-Step-V2; SGLang's registry pins a revision of this repo so re-materializing the model does not drift. The materializer reshapes the flat native-Diffusers release into the base MiniMax-H3 partition layout SGLang's loaders consume: - modelindex.json declares the t2va-only release contract (tasks: ["t2va"], video/audio sigma shifts 10/3, and the trained eight DMD rungs [999, 874, 749, 624, 500, 375, 250, 125]). - overlay/materialize.py re-serializes the…

Excerpt from the card by Kevin Mi.

Identity and Version

Repository
kevin-mi/FastH3-8step-V2-overlay
Publisher
Kevin Mi
Task
Not stated by the source
Modality
Other
Library
sglang-diffusion
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
308e2dd627218c40ae759a93745429800771a625
First published
2026-09-30
Last updated
2026-09-30

Files and Weights

5 files, 12.8 KB in total.

Configuration3 files · 9.8 KB
Documentation1 file · 1.4 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
_overlay/materialize.pyConfiguration8.1 KB —
_overlay/overlay_manifest.jsonConfiguration904 B —
model_index.jsonConfiguration828 B —
README.mdDocumentation1.4 KB —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download from Kevin Mi

Released by Kevin Mi through its official repository on Hugging Face.