MiniMax launches H3 open-weight multimodal generation model
MiniMax H3, a general-purpose multimodal generation model with unified context across text and images, is now available in ComfyUI via API access. Native open-weight support is coming soon, and a text-to-video ComfyUI workflow template has been released on GitHub.
How this story unfolded
3 days · 0 reports · 3 community posts · from Jul 31
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- Qwen 3.6 runs locally on Radeon R9700 and multi-Mac agent farms
- Tool compiles knowledge bases and runs parallel research across Claude, Codex, Pi
- ESP32-S3 board turned into $5 personal AI assistant for Telegram
- Filmmaker releases 'Memories' short film made with H3 and Seedance 2.5
- WorkOS argues REST and MCP are complementary, not competing, for agents