AI video prompts
Use these AI video prompt examples when you already have a keyframe and need controlled camera movement, subject motion, and timing without warping the scene.
Keyframe for image-to-video: premium sneaker on wet asphalt, neon reflection, camera low angle, product label sharp, 16:9. Motion note: slow push-in, rain shimmer only, no product morphing.
Copy into ChatGPT Image / GPT Image; adjust product names and hex colors.
Use a storyboard as the visual reference, then describe only shot order, camera motion, and timing.
Use the uploaded storyboard as reference. Preserve character identity and shot order. Animate a slow opening push-in, a medium tracking shot, and a quiet close-up finish over 8 seconds. Keep backgrounds stable; no panel borders, captions, or character morphing.View the real recipe output
A low-risk commercial motion pattern that protects package shape and label details.
Slow 8% camera push-in toward the product, subtle condensation movement, soft background bokeh, locked label geometry, five seconds, no orbit, no shape change, no added text.
Micro-motion for portraits and character keyframes without face or wardrobe drift.
Locked camera, natural blink once, gentle breathing, slight hair movement from a soft breeze, stable facial identity and wardrobe, four seconds, no lip movement, no camera shake, no body morphing.
Step 1
Generate the still first
Keep the still prompt focused on composition, material, and readable product details.
Step 2
Separate motion notes
Use short motion instructions for the video step instead of asking the still prompt to animate.
Step 3
Reject morphing
If the product shape changes, reduce camera movement and ask for micro-motion only.
Multi-step pipeline: Workflow index · Recipe library