MiniMax open-weights H3-Image: 16MP images in 10 seconds, vLLM ships Day-0 support
AccBalanced · x · 2026-11-11
MiniMax released open-weight image model MiniMax H3-Image: native 16MP resolution, 4K generation in about 10 seconds, multi-reference editing (up to 9 images per request in the release recipe, 16 claimed), 4096-token prompts and dense text rendering. Available via MiniMax API, MiniMax Code and Hailuo AI with 50% off 16MP+ generations during launch week. vLLM-Omni added Day-0 support on both NVIDIA and AMD GPUs for generation and editing.
Related event: MiniMax Open-Sources H3-Image: 16MP Image Generation in ~10 Seconds(22 posts)→
More from Multimodal
- Fable 5.2 Beats Astra on Realism: Better Trees, Terrain, Grass and Water — Angaisb_ · 2026-11-11
- Dreamina Canvas adds motion capture: use video motion as a generation reference — FellMentKE · 2026-11-11
- Adobe Firefly AI Creative Assistant Goes Live at Adobe MAX After Beta Testing — umesh_ai · 2026-11-11
- Fish Audio launches Live 3, a full-duplex voice model that knows when to shut up — bigaiguy · 2026-11-11
- Krea CEO: fewer one-shot demos, more model-collaboration workflows — araminta_k's Tween & Paint shows how — trq212 · 2026-11-11
- 'Make me the most beautiful video you can': Fable 5.2 demo stuns users — teortaxesTex · 2026-11-11