MiniMax-H3 Fused Turbo
4-step video generation with audio
3 min read
A single 21 GB file for ComfyUI by MATLOWAI that bundles the MiniMax-H3 video model with two baked-in LoRAs (lightweight add-ons on top of the base model): lightx2v Turbo for speed and Mystic v2.0 for smoother motion. Under the hood is a merged fl2va transformer with the ref2va weight delta fused in, letting one file handle text-to-video, first/last-frame interpolation, and reference-guided video with synchronized audio—without swapping checkpoints. Baking the adapters in before INT8 (ConvRot) quantization keeps ComfyUI from storing backup copies of patched layers, saving roughly 21 GB of VRAM compared to loading separate files. Ideal for generating 10-second 1152x640 clips quickly, even on 16 GB GPUs.
Key features
- 4-step generation: despite using a baked-in 8-step Turbo LoRA, the model hits its sweet spot at 4 steps (or 4+4 in the two-pass de-rope pipeline).
- Saves ~21 GB of VRAM: merging the LoRAs prior to INT8 quantization eliminates the need to hold duplicates of 200 modified layers in memory at runtime in ComfyUI.
- Crisp audio with SLA: pairing H3 SLA sparse attention with the
res_multistepsampler preserves high-frequency audio detail while speeding up rendering by about 40%. - Ready-to-run workflows for different setups: the repo includes 5 ComfyUI workflows, covering AMD GPUs (ROCm) and a Low VRAM mode with FFN chunking for 16 GB cards.
What you can do
- Generate 10-second 1152x640 videos with audio from a text prompt in a single pass (
01_reference_4step_slaworkflow). - Animate still images and create smooth transitions between a start and end frame using the
04_i2v_fl2v_4step_slagraph. - Keep a character's or object's appearance consistent in motion from a reference image via the
MiniMaxH3ReferenceToVideonode (05_ref2va_4step_slaworkflow). - Smooth out abrupt motion jumps with the two-pass
02_derope_4plus4_slapipeline, or boost dynamics using the externalwarm375adapter.
Example
Drop the main model file into ComfyUI/models/diffusion_models/, load it with the standard UNETLoader node (weight_dtype: default), and drag a workflow from the workflows/ folder onto the canvas. Recommended sampler settings for a 10-second clip (243 frames, 1152x640): res_multistep sampler, simple scheduler, 4 steps, BasicGuider (no CFG), and MiniMaxH3SigmaShift (video 12 / audio 3) paired with the H3 SLA sparse attention node (sparsity 0.90, block 64).
Read more
DetailsSpeed (RTX PRO 6000, 1152x640, 243 frames, SLA): 4 steps — 76 s, 6 steps — 80 s, 8 steps — 103 s, 25 steps — 292 s.
Hardware requirements: in Low VRAM mode on a 16 GB GPU (offloading to 32 GB system RAM), 4-step generation takes 59 s with peak usage of 10.9 GiB VRAM (the standard workflow uses 11.0 GiB and takes 65 s).
Required companion files: you will need the
qwen3vl_32b_minimax_h3_nvfp4_awq encoder, minimax_h3_video_vae_int8_convrot video VAE, minimax_h3_audio_vae_fp32 audio VAE, plus the ComfyUI-MAINodes and SLA node packs.Limitations: the baked-in LoRAs cannot be toggled off or reweighted; under heavy motion, the
warm375 adapter can push 2D animation toward photorealism and cause object duplication.License: MiniMax H3 Community License Agreement (with territorial restrictions); the baked-in Turbo LoRA is licensed under Apache-2.0.














Comments