aptech0081/MiniMax-H3-PDD-ComfyUI
text-to-video model by aptech0081
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
ComfyUI conversions of the official Alibaba PAI MiniMax-H3 PDD acceleration weights. The Ref2VA checkpoints generate video and audio from reference conditioning. Choose PRUNED INT8 WITH HEADS for the smaller native PDD checkpoint. This repository also keeps the full INT8 WITH HEADS and WITHOUT HEADS variants. Both with-heads files contain the merged PDD trunk and 32 video plus 32 audio output heads. They load through native ComfyUI after PR #17157, merged October 18, 2026, without a separate PDD acceleration LoRA or PDD Apply node. Put any baked checkpoint in ComfyUI/models/diffusionmodels/. Put the two custom-node LoRA files in ComfyUI/models/pddacc/. The without-heads checkpoint is the former minimaxh3ref2vapddacc8stepbakedint8convrot.safetensors. It was renamed for clarity; its bytes and SHA256 are unchanged. Existing download links using the old filename need to be updated. The video/audio sigma shifts are 12.0 / 3.0, the native model defaults. are already included. Keep other acceleration LoRAs disabled for this recipe. Four…
Read the full model card ↗ · Preview checked 2026-10-29T02:59:43.345Z
Inside the original model card — Document outline
- MiniMax H3 PDD — ComfyUI LoRAs and baked Ref2VA checkpoints
- Files
- WITH HEADS — native ComfyUI
- PRUNED INT8 WITH HEADS
- WITHOUT HEADS — companion PDD nodes
- Standalone LoRA conversions
- Full checkpoint conversion validation
- SHA256
- Credits and license
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
aptech0081/MiniMax-H3-PDD-ComfyUI is a text-to-video model repository published by aptech0081 on Hugging Face. The source reports the minimax-h3 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- minimax-h3
- Recent downloads (30 days)
- 28,848
- Cumulative likes
- 85
- Hugging Face trending score
- 2
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-08-26T15:03:46.000Z
- Last modified
- 2026-10-20T04:58:44.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: alibaba-pai/MiniMax-H3-Acc-LoRAs, MiniMaxAI/MiniMax-H3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:32.159Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF