MiniMax open-sources H3-Image: 16MP 4K image gen and editing in 10 seconds
MiniMax_AI · x · 2026-11-10
MiniMax officially released MiniMax-H3-Image, an open-weight image generation and editing model.
- Generates 16-megapixel images directly (4096×4096 up to 6272×2688 at 21:9) without an upscaler, in about 10 seconds
- DiT built on the H3 architecture (minus audio layers) with the MiniMax-H3 text encoder, distilled to 6 sampling steps with no classifier-free guidance
- Unified checkpoint handles both text-to-image and image editing with up to 16 reference images
- Available via Hugging Face, API, MiniMax Code, and Hailuo AI; 50% off 16MP+ generations during launch week
Related event: MiniMax open-sources H3-Image: 16MP 4K images in about 10 seconds(20 posts)→
More from Multimodal
- Seedance 2.5 generates a luxury perfume commercial for a fictional fragrance — aftahi_ai · 2026-11-11
- BaoCut Explains Virtual Streamers Like Shadow Puppets — 3 Steps to Add One to Your Videos — dotey · 2026-11-11
- MiniMax H3-Image 2-step LoRA released on Hugging Face with sample gallery — Illustrious_Row_9971 · 2026-11-11
- Magnific Studios Launches Animated Series 'Before the Show', Shares Behind-the-Scenes — CurieuxExplorer · 2026-11-11
- 'Cara Love the Adventurer': AI-Generated Short Film Trailer Released — noLOOPai · 2026-11-11
- 'Digital Love': An AI-Generated Robot Dating Show Short — BotLordBotflix · 2026-11-11