Model reference · open weights
MiniMax-H3-Acc-LoRAs-ComfyUI is an open-weight video model from aptech0081, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
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 Put the LoRA files in ComfyUI/models/pddacc/. Pair FL2VA with an fl2va UNET, Ref2VA with ref2va (bf16 or int8-convrot builds both work). The baked checkpoint goes in ComfyUI/models/diffusionmodels/ instead. 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 exampleworkflows/. Baked Ref2VA trunk (for cards that can't fully load the model) minimaxh3ref2vapddacc8stepbakedint8convrot.safetensors (34 GB) is Comfy-Org/MiniMax-H3's minimaxh3ref2vaint8convrot checkpoint with this repo's Ref2VA trunk LoRA pre-merged at strength 1.0 (dequantize → add → requantize with the same comfy-kitchen int8-convrot kernels ComfyUI itself uses; every tensor keeps its exact dtype, shape and byte length). The PDD head bank is not in this file — it stays runtime, so you still need the node pack and one of the LoRA files above. Why it exists: ComfyUI merges LoRA patches into weights only for modules that fit in VRAM; offloaded modules get a per-forward lowvram patch — the LoRA (plus a dequantize) is re-applied on every step. On cards at the VRAM edge that fixed cost is large: ~2× s/it at 864×480 on a 32 GB RTX 5090 (node pack issue #4). Baking removes the patch term entirely — m
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | aptech0081 |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | minimax-h3 |
| Based on | alibaba-pai/MiniMax-H3-Acc-LoRAs, MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-26 |
| Popularity | 16k downloads / month |
| Likes | 46 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MiniMax-H3-Acc-LoRAs-ComfyUI | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys minimax-h3-acc-loras-comfyui for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-acc-loras-comfyui below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-h3-acc-loras-comfyui","prompt":"a drone shot over a forest"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore