MiniMax AI has launched its new multimodal video model, H3, which is now available through Runway ML and Fal. The model, also referred to as Hailuo-03, supports open weights and can integrate up to nine images, three video clips, and three audio clips to maintain subject, motion, and audio consistency across generations. MiniMax AI is collaborating with Day 0 partners and expresses gratitude to Fal for their support in making H3 accessible to creators. AI
IMPACT This release offers creators a powerful new tool for multimodal video generation with open weights, potentially accelerating innovation in AI-driven content creation.
RANK_REASON Frontier-lab model release with system card
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →