Dual-mode generation
Start from a blank prompt and it uses its 85+ text-to-video models. Upload a still and it switches to the 120+ image-to-video set, using your image as the first frame.
One workspace that turns a text prompt into a clip or a still image into motion, switching automatically between its two model sets depending on what you give it.
It's the platform's dedicated workspace for motion — one canvas covering both generating a clip from text and animating a still you already have.
Start from a blank prompt and it uses its 85+ text-to-video models. Upload a still and it switches to the 120+ image-to-video set, using your image as the first frame.
The catalog tracks new releases as they ship — Seedance 2.0 with its image-to-video and extend variants, and Grok Imagine's text-to-video and image-to-video models are already wired in.
Send a finished clip into Lip Sync Studio for dialogue, or generate the first frame in Image Studio and hand it off here to animate.
Both modes together run 85+ text-to-video and 120+ image-to-video models; here's a sample of what's inside.
The same flow whether you're starting from a written prompt or a still image.
Write a prompt for text-to-video, or upload a still to animate it — the studio picks the right model set for you.
Pick from 85+ text-to-video or 120+ image-to-video models, including the newest Seedance 2.0 and Grok Imagine releases.
Download the clip, or send it into Lip Sync Studio to add dialogue, or Workflow Studio to chain it into a longer pipeline.
This is one of 14 purpose-built workspaces on the platform. Here's where to go next.
Generate from a blank prompt or edit an uploaded photo — 70+ text-to-image and 70+ image-to-image models.
Photorealistic shots with pro camera, lens, focal length and aperture controls.
Animate a portrait you made here, or re-sync lips on an existing video — 9 dedicated models.
Chain this studio's output into video and audio models as one repeatable, node-based pipeline.
Generate and edit AI audio and music from a text prompt.
85+ text-to-video models, 120+ image-to-video models, automatic mode-switching. No subscription, no account required to try it.
Try Free