Video 02 API

MiniMax Video-02 — minimax/video-02

MiniMax Video-02 generates short video clips from a text prompt, with optional image guidance. Describe the subject, action, scene, and camera movement, and the model produces a coherent, motion-rich clip suitable for story beats, ads, and creative prototyping.

Key capabilities

• Text-to-video generation with strong motion and scene coherence
• Optional image input to anchor composition and style
• Camera-direction friendly prompting (follow, pull back, track, tilt, orbit)
• Prompt expansion option to automatically enhance prompts and enable the safety checker

Use cases

• Cinematic shot generation (camera moves, blocking, atmosphere)
• Storyboarding and pre-visualization for short scenes
• Marketing creatives and social clips with clear action cues
• Image-guided variants (keep a reference look while changing motion/camera)

Pricing

Parameters

• prompt (required): What happens in the video (subject, action, scene, camera, style)
• image (optional): Reference image to guide composition/style
• resolution: Output resolution (e.g., 720p, 1080p)
• duration: Video length (seconds)
• enable_prompt_expansion: Enhances the prompt automatically and enables the safety checker

Prompting tips

• Lead with action verbs (runs, spins, juggles, turns, laughs), then add camera language (pull back, track left, tilt up).
• Keep one “main event” per clip; add atmosphere as a second layer (dust, fog, rim light, crowd).
• If using an image, state what must stay consistent (character identity, outfit, composition) and what should change (motion, camera path, mood).