Stable Video Diffusion は、オープンソースの Stable Video Diffusion モデルファミリー（SVD、SVD-XT）をベースとした独立したAI動画ツールです。Stability AI とは一切関係ありません。すべての商標はそれぞれの所有者に帰属します。
Text to Video
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.
How Text to Video works
Describe the scene
Write a prompt describing the look you want for the opening frame.
Generate the frame
A text-to-image step renders your prompt into a still that seeds the video.
Animate with SVD
Stable Video Diffusion turns that frame into a short, coherent motion clip.
Why use our Text to Video
No source photo
Start entirely from a prompt — the model creates the frame for you.
Prompt-driven look
Your description sets the scene, style, and composition of the starting frame.
Coherent motion
SVD keeps the generated motion smooth and anchored to the seed frame.
Text to Video FAQ
Your prompt is first turned into a still image, then Stable Video Diffusion conditions on that frame and animates it into a short clip.
No. Text to Video generates the starting frame from your prompt, so no source photo is required.
Describe subject, setting, lighting, and camera feel. The clearer the prompt, the more on-target the seed frame and resulting motion.
Clips are short — around two to four seconds — matching Stable Video Diffusion's 14 and 25-frame outputs.
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 toolMotion Control
Tune motion bucket and frame count
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.
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