ComfyUI-Spectrum-MiniMax-H3

▶ See it at the source

What they did

ComfyUI nodes that apply Spectrum, a training-free sampling speed-up from a 2026 paper, to the native MiniMax H3 audio-video model. They handle H3's combined audio/video latents.

Worth knowing

• Price: Open source (GPL-3.0)
• License: GPL-3.0
• Status: sourced. We have not run this ourselves yet (no "Tested" badge).
• Quality bar (computed by code): 5/5 (primary source ✓, reproducible ✓, new ✓, example output ✓, safe ✓)

Related

tool▶ demo at source

Hailuo AI

MiniMax's consumer app for its Hailuo video models, with text- and image-to-video plus social-oriented tools.

Demo by MiniMax

Hailuo / MiniMax✓ vendor-checked

model▶ example at source

MiniMax video API docs

MiniMax's platform overview, where to find API access for its video, speech and language models.

Hailuo / MiniMax✓ vendor-checked

tool▶ demo at source

Replicate video collection

Replicate's curated collection of text-to-video models you can run by API, an alternative host to fal.

Demo by Replicate

ReplicateVeoHailuo / MiniMax✓ vendor-checked

tool▶ demo at source

ComfyUI

ComfyUI is the open, node-based app for building image and video pipelines on your own GPU or in the cloud. Most open-model video workflows assume it.

Demo by Comfy Org

ComfyUI✓ vendor-checked

tool▶ demo at source

ComfyUI docs: video

Official ComfyUI tutorial for Wan 2.1: text-to-video with the 1.3B model and image-to-video with the 14B model, including where each model file goes.

Demo by Comfy Org

ComfyUIWan✓ vendor-checked

tool▶ demo on X

ComfyUI Changelog

ComfyUI's release log. Check it to see when new video models get native nodes.

Demo by @ComfyUI

ComfyUI✓ vendor-checked