Skip to content

Repository files navigation

Minimax-H3-Turbo provides MiniMax-H3 Turbo LoRA checkpoints, plus Diffusers batch inference and ComfyUI workflows.

1. Model specs

Model Tasks Training
resolution
Training shifts
(video / audio)
Distillation
steps (NFE)
Recommended inference
steps (NFE)
FL2VA Turbo 4-step v0.1
Diffusers · ComfyUI
FL2VA / T2VA 544p
mixed aspect ratio
12 / 3 4 4
FL2VA Turbo 8-step v1.0
Diffusers · ComfyUI
FL2VA / T2VA 544p
mixed aspect ratio
12 / 3 8 8 / 4
FL2VA Turbo 4-step v1.0 768p
Diffusers · ComfyUI
FL2VA / T2VA 768p
1344x768
6 / 3 4 4
Ref2VA Turbo 4-step v0.1
Diffusers · ComfyUI
Ref2VA 544p
mixed aspect ratio
12 / 3 4 4

Note on shift

For NFE = N, define the N transformer evaluation points on the unshifted grid as q_i = (N - i) / N, where i = 0, 1, ..., N - 1.

For example, with NFE = 4, video shift = 12, and audio shift = 3, the shared grid is q = [1, 0.75, 0.5, 0.25], giving video sigma [1, 0.9730, 0.9231, 0.8000] -> 0 and audio sigma [1, 0.9000, 0.7500, 0.5000] -> 0; each list therefore uses exactly four NFEs.

Note on reference-image resizing

The three reference-image resizing policies used by our workflows are based on the ref_image_size implementation described in ComfyUI's MiniMax H3 R2V reference-image sizing guidance:

Mode Behavior Scale factor
before 32-pixel rounding
match Matches the reference pixel area to the target canvas while preserving the reference aspect ratio. It never upscales a smaller reference. min(1, sqrt(target_area / ref_area))
max Preserves the reference aspect ratio and only scales down references whose short edge exceeds 2048 pixels. min(1, 2048 / ref_short_edge)
diffusers Preserves the reference aspect ratio and forces the short edge to 2048 pixels, matching the original Diffusers behavior. 2048 / ref_short_edge

All three policies keep the reference aspect ratio, use the H3 resolution grid (dimensions rounded to multiples of 32), and avoid cropping the reference content. In our distillation training, we use match, so the reference-image pixel budget follows the target training resolution.

The Ref2VA inference entry point in this repository exposes the same three policies through --reference-resize-mode and defaults to match. Passing --reference-resize-mode diffusers restores the original Diffusers behavior (the fixed 2048-pixel short edge). For our distilled models, we recommend selecting match so inference uses the same resizing policy as training.

2. Diffusers setup and inference

See DIFFUSERS_SETUP_AND_INFERENCE.md for environment setup, checkpoint downloads, test JSON files, and single- or multi-GPU inference commands.

3. ComfyUI inference

See COMFYUI_SETUP_AND_INFERENCE.md for ComfyUI requirements, model installation, inputs, prompts, and run instructions.

Example workflows

Ready-to-import graphs are in example_workflows. The T2VA and I2VA graphs default to FL2VA Turbo 8-step v1.0; the Ref2VA graph uses Ref2VA Turbo 4-step v0.1.

Workflow Task Default resolution
video_minimax_h3_t2v_lightx2v_turbo.json T2VA (text-to-video + audio) 960×544 (16:9, 0.5 MP)
video_minimax_h3_i2v_lightx2v_turbo.json I2VA / FL2VA (image-to-video + audio) 864×480 (16:9, 0.4 MP)
video_minimax_h3_ref2v_lightx2v_turbo.json Ref2VA (reference-to-video + audio) 960×544 (16:9, 0.5 MP)

All graphs wrap the same MiniMax-H3 subgraph. T2VA leaves first_frame / last_frame unconnected; I2VA connects a LoadImage to first_frame, with last_frame optional for first/last-frame interpolation. Ref2VA connects one or more reference images through the reference-input branch.

For detailed workflow inputs and execution steps, see COMFYUI_SETUP_AND_INFERENCE.md.

4. Roadmap

  1. Improve the visual quality and consistency of Ref2VA and FL2VA Turbo.

5. Acknowledgements

Some Ref2VA test cases and reference assets are adapted from public showcases on the Hailuo website and from the MiniMax-H3 discussion on Hugging Face. We thank the community contributors for sharing their test assets and prompts.

Special thanks to the MiniMax-AI/MiniMax-H3 project and the MiniMax team for open-sourcing the MiniMax-H3 model.

About

Distill Minimax-H3 into 4 steps

Resources

Stars

312 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages