AI3D API v2 model
h3-max-image-to-video
Generate a video from a prompt and optional start/end frame images with MiniMax H3 Max. If no frame image is provided, Fal handles the request as text-to-video.
Implementation guide
Use the model-specific llm.txt for request inputs, defaults, provider notes, and a complete AI3D job example. Copy it for your coding agent or open the raw text.