Cointime update: MiniMax released its H3-Image image-generation model on November 11 and published the model weights alongside it. Derived from MiniMax H3, the model supports text-to-image, image reference and image editing, and can generate a 4096×4096-pixel (about 16MP, 4K) image in under 10 seconds — a speed MiniMax says is up to five times that of mainstream models on the market.
MiniMax Releases Open-Weight H3-Image Model for 4K Image Generation
Share on WeChat
Open WeChat → Scan → then tap "…" to send to a chat or Moments.
Tap "…" in the top-right corner to send to a chat or share to Moments.
Related News
45m ago
Polus Executive Warns AI Borrowing Boom Signals Weaker Credit Underwriting
2h ago
Nasdaq Opens Up 0.7% as AI-Linked Stocks Rally on Nvidia Outlook
2h ago
UBS Cuts Nvidia Price Target to $220 from $240
2h ago
ByteDance in talks to add $500M in OpenAI model services via Azure
2h ago
Tencent May Take Longer to Launch Next Hunyuan Model, President Says
4h ago
Xiaomi’s MiMo LLM unit weighs spin-off funding as Lei Jun and Luo Fuli differ