Short answer
Open Create and choose Video to generate from text, or open AI image to video to animate one uploaded image. New videos use 9:16 or 16:9, and the default is Veo 3.1 Fast at 720p, portrait 9:16, and 8 seconds.
Create a video from text
1. Sign in to Typeshutter.
2. Open Create and choose Video.
3. Keep Veo 3.1 Fast for a balanced first result, or choose another model.
4. Write a prompt describing the opening shot, subject action, camera movement, pacing, lighting, and visual style.
5. Choose 9:16 for portrait or 16:9 for landscape. Adaptive ratio is unavailable for new videos.
6. Choose a supported resolution and duration. Typeshutter supports 4, 8, or 12 seconds, although each model may offer a smaller subset.
7. Add image references if the selected model supports them, then start the generation.
Animate one image with AI image to video
1. Open AI image to video from the Create picker or the AI tools catalog.
2. Upload one clear photo, illustration, product image, or artwork.
3. Optionally describe the subject, environment, or camera motion. Leave the direction blank to let Typeshutter privately analyze the image and choose a natural continuation.
4. Choose 9:16 or 16:9 and the resolution and duration supported by your selected model.
5. Start the generation.
Typeshutter center-crops the uploaded image to the selected ratio before generation. That prepared image becomes the exact opening frame, and the video continues forward from the visible moment as one coherent shot. The AI creates a plausible continuation; it does not recover real footage or reveal what actually happened before or after the photo.
The motion field stays blank unless you type in it. Typeshutter does not display its private scene analysis or internal generation instructions. If a prompt needs revision, any suggested replacement is based only on the direction you entered.
Create from image
Create from image in Video mode is a different workflow. Typeshutter analyzes the still and writes a self-contained video prompt describing the opening shot, motion, camera movement, pacing, and continuity.
The analyzed image is not attached automatically. Add it separately as a reference if you want the provider to use it. Grok Imagine Video 1.5 requires an image reference.
Notes
• Video generation usually takes longer than image generation.
• A strong video prompt describes motion and camera behavior, not only the subject.
• Video is charged once for the configured clip. The charge depends on the model, resolution, duration, and accepted reference count.
• The dedicated AI image-to-video tool accepts exactly one uploaded image.
• Veo and Grok accept one image in the standard reference workflow. Seedance 2.0, Fast, and Mini accept up to nine.
Troubleshooting
• If a setting disappears after changing models, choose one supported by the newly selected model.
• If the image-to-video crop removes important content, choose the other ratio or start with an image whose subject is closer to the center.
• If Veo or Grok rejects extra references, keep one image.
• If a video remains processing, allow more time before retrying.
• If the provider result is unknown, wait for reconciliation rather than submitting repeated retries.