MiniMax H3
An open-weight video model with synchronized native audio. ComfyUI provides a local single-GPU template with dynamic offload; the publisher also documents a separate SGLang multi-GPU route.
What do you want to do?
Choose a task. Get the software, files, settings, and steps to run it.
Generate MiniMax H3 video with audio in ComfyUI
Generate a short local MiniMax H3 video with synchronized sound in ComfyUI using the supported NVIDIA or Apple Silicon package for your machine.
Generate MiniMax H3 videos with FreeVideo
Install FreeVideo’s managed ComfyUI workspace on Windows, Linux, an experimental Apple Silicon Mac, or a rented RunPod GPU. Generate and save a MiniMax H3 video with audio, then try image-to-video, previews, and optional automation.
Create MiniMax H3 video on a rented GPU
Use one rented NVIDIA GPU and ComfyUI’s official MiniMax H3 text-to-video graph to make and download a short clip with synchronized audio.
Open a guide for its software, hardware requirements, and setup steps.
At a glance
- Parameters
- 33B
- Architecture
- Dense omni-modal transformer
- License
- MiniMax H3 Community License Agreement
- Software
- ComfyUI, SGLang
Will it run on your machine?
Save your machine to see a personalized rating and its reasoning.
Add my hardwareBest for
- Generate local text-to-video with synchronized audio using the official ComfyUI template.
- First/last-frame guided video generation.
Tradeoffs
- The separate SGLang publisher deployment is multi-GPU.
- Review the community and commercial-use license before deploying.
Ways to run it
ComfyUI · Windows, Linux
Official ComfyUI text-to-video template uses optimized H3 weights and dynamic offload; total model footprint is about 42.5 GB.
Official instructionsSGLang · Linux
The documented FL2VA base checkpoint can run locally on rented GPUs.
sglang serve --model-path MiniMaxAI/MiniMax-H3 --num-gpus 4 --ulysses-degree 4 --performance-mode speed --host 0.0.0.0 --port 30010 --model-variant fl2vaExplore its uses
Keep exploring
Wan-Animate-2 · 14B
Animate a character from a driving video, with text control over the camera viewpoint.
Wan2.1
Explore 2 versions of Wan2.1. Compare model sizes, packages, hardware requirements, and available setups.
LTX 2.5
LTX 2.5 is a Lightricks model (repository: Lightricks/LTX-2.5) associated with an image-to-video pipeline and released under the ltx-2.x-community-license-agreement. Its official model card lists multimodal video, audio, and audio-video task tags, including image-to-video, text-to-video, video-to-video, image-text-to-video, audio-to-video, text-to-audio, video-to-audio, audio-to-audio, text-to-audio-video, image-to-audio-video, and image-text-to-audio-video. The card also indicates ComfyUI and ltx-2.5 tags, a demo link, supported languages (en, de, es, fr, ja, ko, zh, it, pt), and a gated access flow with privacy policy acknowledgement.