animate_pixminimax
Animate a static frame into a fluid clip from a text motion description. Generate 4-40 frames with optional keyframe interpolation for longer animations.
Instructions
Beta (tier 1+ subscription): animate a single frame from a text description of the MOTION using the PixMiniMax engine (MiniMax H3). Best for fluid, longer clips — 4 to 40 frames (multiples of 4) at up to 256x256. Result holds frame_count + 1 images: index 0 is your unchanged input frame. Optional last_frame makes it a keyframe interpolation. Priced by clip length and size (about 1-12 generations); sizes just above 64 or 128px are cheaper than just below. Typically takes 1-5 minutes. Use animate_with_text_v3 for the standard engine.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | Seed for reproducible generation (0 = random, default 0) | |
| direction | No | Facing direction of the sprite (south = towards camera). Only used with enhance_prompt to hold the facing and aim attacks that way. Omit to let the enhancer read it from the image | |
| last_frame | No | Optional end pose, same size as first_frame — the motion is generated between the two | |
| description | Yes | The motion to generate (e.g. 'walking forward', 'sword slash', 'flame flickering'). Describe movement, not appearance. Max 1000 chars | |
| first_frame | Yes | Starting frame (max 256x256) | |
| frame_count | No | Frames to generate — a multiple of 4 from 4 to 40 (default 8) | |
| no_background | No | Return frames on transparency; an opaque input is cut out of its first frame before animating (default true) | |
| enhance_prompt | No | Expand description into a detailed PixMiniMax motion prompt before generating (+0.05 generations; expanded text returned as enhanced_prompt). Default false | |
| drift_threshold | No | Color de-flicker sensitivity. Frames whose foreground drifts from the first frame beyond this are corrected toward it; 0 corrects every frame, higher corrects fewer. Omit for the default |