Minimax Video-01

MiniMax Video-01 — minimax/video-01

MiniMax Video-01 is a text-to-video (T2V) model for generating short, coherent clips from a single prompt. It’s built for cinematic pacing, stable scene continuity, and prompt-faithful motion, making it a strong default for story beats, product shots, and concept trailers.

What it’s good at

• Text-to-Video (T2V): generate a complete clip from a prompt
• Cinematic language: responds well to shot descriptions and camera cues
• Coherent motion: maintains continuity across frames for simple-to-moderate action
• Fast iteration: great for rapid creative exploration and storyboard-style outputs

Inputs

• Prompt (required): describe subject, action, environment, lighting, camera, and style
• Image (optional, if supported in your deployment): provide a reference frame to steer the look
• Enable prompt expansion (optional): automatically expands/optimizes your prompt for better visual quality

Key parameters

• enable_prompt_expansion:

• On: better visual richness and fewer “under-specified” results

• Off: tighter control, closer to your exact wording (often best for structured prompts)

Prompting tips

• Use a “director brief” structure:

• Subject: who/what is on screen

• Action: what changes over time

• Scene: where + time of day + lighting

• Camera: framing + movement + transitions

• Style: mood + medium + references (optional)

• Prefer one clear main action per clip (then iterate).

• If you need stronger motion, add pace and intent: slowly, rapidly, abrupt cut, smooth dolly-in, handheld shake.

Use cases

• Concept trailers & story beats: quick visual drafts for narrative sequences
• Marketing clips: product mood videos and brand-style visuals
• Social content: punchy short clips with strong camera direction
• Pre-visualization: test shots, lighting, and staging before production

Pricing