FastVideo-Minimax-FastH3-Preview-v0.1

A few-step (4-step) distillation preview of MiniMax-H3, the 33B dual-modality (video + audio) diffusion transformer — distilled with data-free DMD2 by the FastVideo team.

The base model samples with 50 denoising steps; this student walks a 4-step grid on the release's shift-12 rectified-flow schedule (12.5× fewer transformer evaluations), generating synchronized video and audio in one pipeline call.

Preview status (v0.1): this is an early training checkpoint (step 1400 of a 4000-step run) published for evaluation and integration work. Sample quality is still maturing; expect a stronger release checkpoint from the same run.

What's in the repo

Diffusers-format (modular pipeline) layout. Only the transformer/ weights differ from the base release — the distilled student, in bf16. All other components (Qwen3-VL text encoder, video/audio VAEs, tokenizer, processor, schedulers) are unmodified copies of the base release, included so the repo is self-contained.

The student was trained with block-sparse video attention (VSA, 64-token tiles, 90% sparsity) and carries its trained sparse-gate parameters (attn.to_gate_compress); it can be run dense (default) or with VSA for additional inference speedup.

Usage (FastVideo)

from fastvideo import VideoGenerator

gen = VideoGenerator.from_pretrained(
    "FastVideo/FastVideo-Minimax-FastVideo-Minimax-FastH3-Preview-v0.1",
    num_gpus=1,
)
video = gen.generate_video(
    prompt="<your H3-format multimodal prompt>",
    num_inference_steps=4,   # the distilled grid
    guidance_scale=1.0,      # the base model is guidance-distilled
)

Prompts follow the MiniMax-H3 multimodal prompt format (integrated_multimodal_description: ... overall_soundscape: ...); see the base model card for the prompting guide.

Training summary

• Method: data-free DMD2 (distribution matching distillation) — student / frozen teacher / trained fake-score critic, backward-simulation rollout (the student walks its own 4-step sampling grid during training), x0-space critic regression, shifted score-time sampling matched to the dual video/audio noise clocks (shifts 12 / 3).
• Student grid: 4 steps on the release sampler's shift-12 schedule.
• Attention: student trained with VSA block-sparse attention (64-token tiles, 90% video-tile sparsity); teacher and critic dense.
• Data: text prompts only (data-free) — ~258k prompts (VidProM-H3 + synthetic t2va prompt set); no video data used.
• Precision: fp32 master weights, bf16 compute.
• Hardware: 32× NVIDIA GB200.

Limitations

• Preview checkpoint — quality below the base model's 50-step sampling, especially on fine motion and audio detail; improves with training.
• Inherits all content limitations and usage restrictions of the base model.
• The 4-step grid is what the student was trained for; other step counts are off-distribution.

License

Distributed under the MiniMax H3 Community License (see LICENSE), inherited from the base model. Review the license (including its territory and acceptable-use terms) before use or redistribution.

Notes

• The transformer_ref component (reference-conditioning variant) is not packaged here; its entry in modular_model_index.json points at the base MiniMaxAI/MiniMax-H3 repo and is fetched from there if used. This preview distills the text-to-video+audio path only.