You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

TaoMate-H3 3-Step LoRA (ComfyUI)

Official TaoMate-H3 3-step LoRA from Alibaba TaoLive AIGC Team, converted for ComfyUI.

Allows generating video + audio with MiniMax H3 in just 3 steps.

Turbo 4-step v1.2	TaoMate MAXQUALITY (BF16)	TaoMate LIGHT (FP16)
▶️ Watch Video	▶️ Watch Video	▶️ Watch Video

File	Rank	Precision	Size	Recommendation
`taomate_h3_3step_MAXQUALITY_bf16.safetensors`	128	BF16	1.2 GB	Best Quality
`taomate_h3_3step_LIGHT_fp16.safetensors`	128	FP16	1.2 GB	Good Alternative

Works best with the FL2VA version of MiniMax H3.

All tests were performed with the same prompt, 5 seconds duration, and 1 MP resolution.

Model + LoRA	Steps	Generation Time
FL2VA pruned int8 + Turbo 4-step v1.2	4	474.30 sec
FL2VA pruned int8 + TaoMate MAXQUALITY	3	373.22 sec
FL2VA pruned int8 + TaoMate LIGHT	3	380.59 sec

Model + LoRA	Steps	Generation Time
FL2VA pruned int8 + Turbo 4-step v1.2	4	130.51 sec
FL2VA pruned int8 + TaoMate MAXQUALITY	3	102.81 sec
FL2VA pruned int8 + TaoMate LIGHT	3	104.84 sec

Conclusion: TaoMate 3-step is approximately 21–27% faster than Turbo 4-step while delivering similar or better quality.

What was done:

Keys renamed from blocks.*.lora_a / lora_b → diffusion_model.blocks.*.lora_down.weight / lora_up.weight
Added diffusion_model. prefix
Precision converted to BF16 and FP16
No fine-tuning and no merging with the base model

Converted for the ComfyUI community.

Base model

Adapter

(128)

this model