Downloads · 30 days
461
34% of all-time downloads
ddalcu/MiniMax-H3-REF2VA-MLX-Serve-8bit
MiniMax-H3-REF2VA-MLX-Serve-8bit is a text-to-video model from ddalcu. Use it when you need video from a text prompt. It is set up for mlx. The card lists the license as other.
8-bit affine (group size 64) conversion of MiniMaxAI/MiniMax-H3 (REF2VA) for mlx-serve, running natively on Apple Silicon. The DiT denoises video and stereo audio jointly in one packed sequence.
Downloads · 30 days
461
34% of all-time downloads
All-time downloads
1.3K
Public
Repo size
69.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors69.3 GB · 100%
From the Hugging Face model README
8-bit affine (group size 64) conversion of MiniMaxAI/MiniMax-H3 (REF2VA) for mlx-serve, running natively on Apple Silicon. The DiT denoises video and stereo audio jointly in one packed sequence.
Text-to-audio-video conditioned on reference images, videos and audio, for character / style / scene continuity.
Self-contained: weights, both VAEs and the tokenizer in one directory. Upstream
splits these across Comfy-Org/MiniMax-H3 (weights, no tokenizer) and
MiniMaxAI/MiniMax-H3 (tokenizer).
Quantized: the DiT and text-encoder matmul weights. Kept dense: gathered embedding tables, the checkpoint's fp32 islands (patch projections, output heads, time embedder) and both VAEs.
Note that quantization here buys FOOTPRINT, not speed — the workload is compute-bound at roughly 192,000 FLOPs per weight byte.
This one takes reference images, clips and audio. It cannot do first/last-frame
conditioning. The FL2VA packs
(8-bit,
4-bit) are the
other way round: keyframes, no references. They are two checkpoints, not two
modes of one, and the files are otherwise identical, so check config.json's
tasks if you are unsure which you have.
Pass them on POST /v1/video/generations:
| field | takes | cap |
|---|---|---|
ref_images | base64 PNG/JPEG | 9 |
ref_videos | {"frames": [b64, ...], "audio": "<b64 wav>"} objects | 3 |
ref_audios | base64 WAV, any rate or channel count | 3 |
At most 12 files across all three. Labels are 1-based per type, in the order
images, then videos, then standalone audio, and a clip's own soundtrack takes
its <Audio j> label immediately before that clip's <Video k>. Reference
rows ride every sampling step, so each reference makes the run slower; a
reference video is snapped down to the frame ladder and truncated to the length
you are generating.
The MLX Core app drives all of this from the Media window, including the examples above.
These are MODIFIED files. The transformer and text encoder are quantized to 8-bit; see MODIFICATIONS.md for the full list. The VAEs and tokenizer are unmodified copies.
Powered by MiniMax H3. Licensed under the MiniMax H3 Community License Agreement -- see LICENSE and NOTICE, both included here.
Territorial restriction. The Agreement defines the Applicable Territory as worldwide EXCLUDING the European Union, the United Kingdom, the Republic of Korea and the United States of America, and Section V.4 prohibits use, reproduction, modification, distribution and display outside it. Check whether your jurisdiction permits you to use these files before downloading them.