Make or upload the frame
Generate it with a text-to-image model or drop your own render.
Uncensored image-to-video
Upload a still — a generated frame, a render, a synthetic character — and describe what moves. The first frame is locked; the model only has to animate. Optionally give a last frame to control where the shot ends.
How it works
Generate it with a text-to-image model or drop your own render.
“She turns from the window, camera pushes in, rain on glass.”
Reshoot the motion, not the frame.
You give
You get
Under the hood
Each model lists its own price and content policy. The spicy route is MiniMax H3; other models follow their vendor’s rules.
FAQ
Yes. One still animates; a first and last frame controls where the shot lands. Two nudes of a consenting adult is that job. Celebrity or non-consensual photos are out of scope.
Yes — the first frame is a hard constraint, which is why this is the reliable way to keep a character consistent across a scene.
Only with their consent and only adults. Unauthorised real-person imagery is out of scope.
Match the target aspect ratio (9:16 for vertical, 16:9 for film) at 1080 px or more on the short edge.
Enter an invite code to open the tool in Chat, or join the waitlist from this page. We open seats in batches and prioritise the tools people ask for most.
Related tools
Invite code opens the tool. No code — join the waitlist; the most-requested tools open first.
Early access
Chat is invite-only for now. Enter a code, or leave your email and we will count the request.