Stable Video Diffusion é uma ferramenta de vídeo IA independente baseada na família de modelos open source Stable Video Diffusion (SVD, SVD-XT). Não possui afiliação com a Stability AI. Todas as marcas registradas pertencem aos seus respectivos proprietários.
Motion Control
Motion Control gives you direct access to Stable Video Diffusion's key dials — the motion bucket, frame count, and target fps — so you can fine-tune exactly how much a still image moves.
How Motion Control works
Upload your image
Drop in the still you want to animate as the conditioning frame.
Set the dials
Adjust the motion bucket, frame count, and fps to shape the movement.
Generate and compare
Render the clip, then re-run with new settings to find the right feel.
Why use our Motion Control
Motion bucket
Choose a low value for subtle drift or a high value for energetic motion.
Frame count
Switch between 14-frame and 25-frame outputs for shorter or longer sequences.
Repeatable results
Fixed settings make it easy to reproduce and refine a look across runs.
Motion Control FAQ
The motion_bucket_id is a Stable Video Diffusion parameter that controls how much movement the model adds — low values produce subtle motion, high values produce dramatic motion.
More frames produce a longer, smoother sequence. The base SVD model outputs 14 frames while SVD-XT and SVD 1.1 output 25.
Conditioning on target fps changes the pacing of the motion, letting you tune how fast the generated sequence plays back.
Yes. Reusing the same image and settings makes generations repeatable, which is ideal for refining a look.
Start free with included credits, then continue with a paid pack.
More tools & models
Keep creating with the rest of the Stable Video Diffusion toolkit.
Image to Video
Animate a still with Stable Video Diffusion
Image to Video uses Stable Video Diffusion to turn a single still image into a short, coherent motion clip. Upload a frame and SVD conditions on it to generate smooth movement while keeping your subject anchored.
Open toolText to Video
Turn a prompt into a Stable Video Diffusion clip
Text to Video pairs a text-to-image step with Stable Video Diffusion: your written prompt becomes a starting frame, then SVD animates it into a short clip — no source photo required.
Open toolSVD-XT
25-frame Stable Video Diffusion
SVD-XT extends Stable Video Diffusion to 25 frames for longer, smoother motion that holds together better than the 14-frame base model.
ExploreSVD 1.1
Refined 25-frame consistency
SVD 1.1 fine-tunes SVD-XT at fixed conditioning settings for more consistent, higher-quality output with reduced flicker and artifacts.
Explore