README.md

metadata

license: apache-2.0
base_model:
  - alibaba-pai/MiniMax-H3-Acc-LoRAs
  - MiniMaxAI/MiniMax-H3
pipeline_tag: text-to-video
tags:
  - comfyui
  - lora
  - minimax-h3
  - video
  - audio
  - distillation

MiniMax-H3 Acc LoRAs — ComfyUI conversion

ComfyUI-key repackaging of the official alibaba-pai/MiniMax-H3-Acc-LoRAs 8-step PDD acceleration LoRAs for MiniMax-H3 — full audio+video generation in 8 (or 4) sampler steps, CFG-free.

These are not plain LoRAs. Each file carries a rank-64 trunk LoRA plus a Parallel Decoding Distillation head bank (32 per-interval final-layer projections per modality, PDD — arXiv:2607.26004). Loading them requires the companion custom node pack:

➡️ Jalen-Brunson/ComfyUI-MiniMax-H3-PDD-Acc (also loads the original alibaba-pai files directly — this repo just saves you the in-memory conversion and gives you inspectable standard LoRA keys).

Files

File	Base trunk	sha256
minimax_h3_fl2va_pdd_acc_8step_comfyui.safetensors	MiniMax-H3 FL2VA	1dce71b9…5cda0ea
minimax_h3_ref2va_pdd_acc_8step_comfyui.safetensors	MiniMax-H3 Ref2VA	5531fa0d…bdc78a1

Put them in ComfyUI/models/pdd_acc/. Pair FL2VA with an fl2va UNET, Ref2VA with ref2va (bf16 or int8-convrot builds both work).

Usage (recipe is mandatory)

UNETLoader → MiniMaxH3SigmaShift (12/3) → MiniMax H3 PDD Acc LoRA (Apply) → BasicGuider (CFG 1.0), sampler euler, sigmas = the Apply node's sigmas output (the trained PDD block boundaries) into SamplerCustomAdvanced. Strengths 1.0, nfe 8 (4 is also official). Remove other distill LoRAs (turbo); don't stack step-caching nodes. A ready-to-run workflow ships in the node pack's example_workflows/.

What was converted

Trunk LoRA renamed from diffusers to ComfyUI H3 keys (diffusion_model.*.lora_A/B.weight

• .alpha, 258 modules):

• to_q/to_k/to_v → attn.qkv_proj: concatenated lora_A, block-diagonal lora_B, alpha ×3 (keeps the per-branch scale exactly 1.0)
• ff.net.0.proj → mlp.fc1: SwiGLU [value;gate] → [gate;value] lora_B row half-swap
• to_out.0 → attn.out_proj, ff.net.2 → mlp.fc2, adaln_proj.linear copied 1:1 (modulation layouts verified bit-identical between the two implementations)
• token_refiner.refiner_blocks.N → token_refiner.blocks.N

The PDD head bank (proj_out [32,96,5376], audio_proj_out [32,32,5376] + biases) is kept byte-for-byte unchanged. Conversion is verified bit-identical to what the node pack computes in memory from the original files, and the converter CLI + 13-test suite live in the GitHub repo. Full provenance (source file sha256, transform description) is embedded in each file's safetensors metadata.

Credits

All training credit to alibaba-pai (Apache-2.0 release) and the PDD authors (Shaul et al.); base model by MiniMaxAI. This repo is a format conversion only.