MiniMax-AI/awesome-minimax-h3-integration

MiniMax-AI/awesome-minimax-h3-integration

Stars: 3

Forks: 1

Open issues: 0

Created: 2026-08-13T05:47:03Z

Pushed: 2026-08-14T22:47:52Z

Default branch: main

Fork: no

Archived: no

README:

MiniMax H3 Integrations

A community-maintained index of checkpoints, tools, and workflows for MiniMax H3, ordered by developer interest.

Official resources

• MiniMax-H3 official model card · official repository
• Video Prompt Writing Guide — Base (FL2VA)
• Video Prompt Writing Guide — Reference (Ref2VA)
• ComfyUI day-0 blog post · tutorial

Start here

This navigation guide is not a complete compatibility list.

| Goal | Start with | | :--- | :--- | | Run on your GPU | [Run locally](#models) — pick a stack from the [VRAM table](#recipes-vram) | | Work with audio | `comfyui-minimax-h3-audio-T8` and [audio VAE](#components-vae) | | Build in ComfyUI | Official tutorial · [Workflows & nodes](#nodes) | | Write better prompts | [Prompting](#recipes-prompt) | | Make it faster | [Speed](#speed) | | Fine-tune it | [Training & LoRAs](#training) | | Serve it as an API | [Serving H3](#partners) | | Run on Apple Silicon | `antirez/h3.c` |

Run it locally

MiniMax-H3 generates video with native stereo audio from text, images, video, and audio inputs. It supports clips up to 2K and 15 seconds. Two base variants exist:

• H3-Base-FL2VA (first-and-last-frame mode) — accepts zero, one, or two input images. Zero images for text-to-video; one image for first- *or* last-frame-to-video; two images for first-and-last-frame-to-video.
• H3-Base-Ref2VA (omni-reference mode) — accepts up to 9 images, 3 video clips (2–15 s each), and 3 audio clips, for a maximum of 12 files total.

Checkpoints are the same size. FL2VA, trained only with keyframes, typically yields better raw output. Ref2VA accepts more reference material but has lower base quality; the [Ref Patch](#refpatch) can partially bridge this gap.

By VRAM and hardware

Find your GPU in the table, then use the notes to inform your configuration.

| Situation | Stack | Why this combination | | :--- | :--- | :--- | | 24 GB, first run | pruned_int8_convrot DiT (19.53 GiB) + TE nvfp4_awq (14.61 GiB) + `ComfyUI-MiniMaxH3-Easy` | Easy routes T2V, I2V, first/last-frame, and reference input through a single Media port. Sampling, LoRAs, and decoding remain outside the node for later modification. | | 24 GB, want speed | The above + TE-Speed-MiniMaxH3-OSS + Turbo v4_step600_ema at 6–8 steps | The maintainer reports about 45% less work from cache reuse. It patches ComfyUI core, so keep the revert command handy. 6–8 steps reduce Turbo motion smear. | | 12–16 GB | Pruned Q4_K_M GGUF (10.64 GiB) or pruned nvfp4 (11.67 GiB) + TE Q2_K (7.91 GiB) + fp8mix VAE pair | GGUF offers the most size options, beneficial for tight memory. IQ1_S is smaller at 3.78 GiB, but quality noticeably drops. | | 8 GB | DiffSynth-Studio NF4 path | The project states 8 GB as its minimum for this path. Offloading performs most work here; expect slow performance, not just small memory footprint. | | RTX 50-series / Blackwell | NVIDIA Sol-Attn | 1.14–1.44× faster than SageAttention with −37 % MLP peak VRAM, measured on a 5090. SM89–SM121, Triton 3.6.0. Also unlocks Blackwell-only hybrid-NVFP4 checkpoints. | | Multi-shot / long video | `ComfyUI-H3-Motion-Context` | H3 generates in blocks up to 15 s. Motion-Context feeds the previous block's final frame and audio forward, preserving motion direction and speed. | | Storyboard / timeline | `ComfyUI_MiniMaxH3_Director` | Five importable templates: t2v, fl2v, r2v, v2v, and rv2v. | | Inpaint / local edit | `scraed/LanPaint` | v2.1.0 fixed H3 support. Training-free video and audio inpainting. | | Apple Silicon | `antirez/h3.c` (MIT, Metal-native) | h3.c supports T2V/A, first-last-frame, and ordered Ref2VA references end-to-end, with M3 Max / M5 Max performance optimization ongoing. | | One-command local | `open-video-ai/open-video` | "Ollama for video models" — install · pull · run. |

Checkpoints

| Source | What it is | Files | Total | | :--- | :--- | :---: | ---: | | MiniMaxAI/MiniMax-H3 | Original diffusers weights — transformer/ (FL2VA) and transformer_ref/ (Ref2VA) at 14 shards / 61.73 GiB each, plus text encoder, video VAE, audio VAE, and self-contained FL2VA/ and Ref2VA/ pipeline folders | 280 | 464.2 GiB | | Comfy-Org/MiniMax-H3 | ComfyUI-repackaged single-file weights — 10 diffusion models, 3 text encoders, video + audio VAE | 17 | 433.2 GiB |

| Variant | Name | Precision | Size | Download | | :--- | :--- | :---: | :---: | :---: | | FL2VA | minimax_h3_fl2va | ![bf16][badge-bf16] | 61.73 GiB | [![][gh-Comfy--Org]](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_bf16.safetensors) | | FL2VA | minimax_h3_fl2va | ![int8][badge-int8] | 31.70 GiB | [![][gh-Comfy--Org]](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_int8_convrot.safetensors) | | FL2VA | minimax_h3_fl2va_pruned | ![bf16][badge-bf16] | 37.46 GiB | [![][gh-Comfy--Org]](https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_fl2va_pruned_bf16.safetensors) | | FL2VA | minimax_h3_fl2va_pruned | ![fp8][badge-fp8] | 19.52 GiB |...