| --- |
| license: other |
| license_name: minimax-h3-community |
| license_link: LICENSE |
| base_model: FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2 |
| tags: |
| - video-generation |
| - minimax-h3 |
| - lora |
| - distillation |
| - few-step |
| - comfyui |
| --- |
| |
| # MiniMax H3 FastH3 4-Step LoRA (ComfyUI) |
|
|
| LoRA extraction of [FastVideo-Minimax-FastH3-Preview-v0.2](https://huggingface.co/FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2), |
| the 4-step DMD2 distillation of MiniMax-H3 FL2VA, as the weight difference against the base |
| [Comfy-Org fl2va release](https://huggingface.co/Comfy-Org/MiniMax-H3). Apply to any fl2va base |
| model to sample in 4 steps instead of 50; guidance-distilled, so cfg 1.0. |
|
|
| ## Files |
|
|
| | file | for | size | |
| |---|---|---| |
| | `loras/..._lora_pruned_rank128_fp16` | `minimax_h3_fl2va_pruned_*` bases (recommended) | 1.33 GB | |
| | `loras/..._lora_pruned_rank64_fp16` | same, smaller | 0.71 GB | |
| | `loras/..._lora_full_max256_avg253_fp16` | full (non-pruned) fl2va bases only | 5.06 GB | |
|
|
| The pruned and full variants are not interchangeable: the adaln projections differ between the |
| two base layouts (see below). |
|
|
| ## Usage |
|
|
| Standard **LoRA Loader (model only)** at strength 1.0 on the matching fl2va base, then sample with |
| **4 steps, euler, simple scheduler, cfg 1.0** (this reproduces the trained ladder |
| `[999, 749, 500, 250]` under the model's shift-12/3 schedule). Other step counts are |
| off-distribution per the FastVideo model card. fl2va / t2va only; there is no ref2va student. |
|
|
| ## Extraction |
|
|
| Layer-by-layer SVD of the weight difference (student minus base), following the |
| [KJNodes](https://github.com/kijai/ComfyUI-KJNodes) `LoraExtractKJ` recipe: rank 256 standard, |
| bias diffs included, no quantile clamp, fp16 output, with exact `svd_linalg` instead of |
| `svd_lowrank`. Lower ranks are truncations of the same SVD. Norm weights ship as `.diff`, |
| biases as `.diff_b`. |
|
|
| Two things specific to this model: |
|
|
| - **Pruned adaln refit.** The pruned bases replace the time embedder with an 8-dim curve table, |
| so ordinary adaln LoRA keys cannot apply there. The pruned variant instead refits the student's |
| adaln projections onto the base's `adaln_t_table` (least squares over the 1025-point grid, |
| residual ~1e-5) and stores them as exact `.diff` keys, tiny at `[out, 8]`. |
| - **The delta is mostly not low-rank.** FastH3 is a full fine-tune saved in bf16; each layer's |
| difference is a strong low-rank head plus a flat rounding-dither tail no rank can carry. The |
| LoRA captures the distillation direction well but is not a perfect stand-in for the full |
| checkpoint. |
|
|
| Measured on a live 4-step run (960x544, 73 frames, same seed/prompt, PSNR vs the actual FastH3 |
| checkpoint; ceiling is the same student under a different quantization): |
|
|
| | run | PSNR | |
| |---|---| |
| | base, no LoRA | 14.6 dB | |
| | base + rank 64 | 17.1 dB | |
| | base + rank 128 | 17.6 dB | |
| | base + rank 256 | 17.7 dB | |
| | FastH3 itself, different quant (ceiling) | 19.9 dB | |
|
|
| Rank 128 is the sweet spot; rank 256 adds almost nothing at double the size. Visually all ranks |
| land on FastH3's composition and sharpness. |
|
|
| ## Credits |
|
|
| - [FastVideo](https://github.com/hao-ai-lab/FastVideo) (hao-ai-lab) for the FastH3 distillation |
| - [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) (MiniMax) and the |
| [Comfy-Org repack](https://huggingface.co/Comfy-Org/MiniMax-H3) used as the base |
| - [Kijai](https://github.com/kijai/ComfyUI-KJNodes) for the extraction recipe and node math |
| - Extraction planned, executed, and verified with the help of |
| [Claude](https://claude.com/claude-code) (Claude Fable 5, via Claude Code) |
|
|
| Distributed under the MiniMax H3 Community License (see [LICENSE](LICENSE)), inherited from the |
| base model. Review its territory and acceptable-use terms before use or redistribution. |
|
|
