Story
MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video
1 report
1 website
1 discussion
Latest report
Overview
MiniMax H3 is an open-weights omni-modal video model that supports real stereo sound and 2K output. It is optimized for ComfyUI and can run locally on a 3060 GPU, allowing users to generate video from text, images, video, or audio inputs.
Summary from blog.comfy.org.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · blog.comfy.org
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-08-03.
- Praise: The results are spectacular, with users highlighting impressive performance on their GPUs — this kind of quality makes the wait worthwhile.
- Praise: Open weights are a massive win for the community, democratizing access and staving off runaway costs from proprietary models.
- Praise: The mouse render is surprisingly good; several clips show a significant leap in quality compared to current SOTA models.
- Praise: The ability to prune modulation weights with no loss in output quality is a game-changer, making models more efficient without sacrificing performance.
- Concern: Some comments suggest that the aesthetic quality looks bland and generic, raising questions about the model's creative capabilities.
- Concern: There's skepticism regarding whether MiniMax H3 can handle logical or technical reasoning well, especially in non-text domains like electronics.
- Concern: Despite impressive results, there's a lingering doubt about the model's overall readiness, with some claiming it's still behind leading models like Seedance 2.0.