Skip to content
PromptMotion

By minimax

MiniMax H3

MiniMax H3 is an open, general-purpose multimodal video model that understands text, image, video and audio inputs. It supports text-to-video, image-to-video with first and/or last frames, reference-based creation and video editing. Output is 768P or 2K for 4–15 integer seconds; prompts accept up to 7,000 characters. Reference inputs allow up to 9 images, 3 videos and 3 audio clips, with at most 12 mixed files. MiniMax H3 Max is a faster fal.ai post-trained variant with 480P and 768P output.

7 cases · 7 with a prompt

MiniMax H3 cases