Two tools.
One page.
Turn your photos and a written scene description into a new AI video. Video to Prompt is not open yet; you can view its planned workflow. Image to Video is open for accounts with eligible credits. Purchases remain closed.
Image to Video
Add 1–4 photos of yourself and describe a scene. The AI model creates a brand-new clip with sound. Photos only: no face swap, no editing of existing footage.
Video to Prompt
AI watches your clip and writes the prompt: subject, scene, action, camera, composition, light and sound. Copy it anywhere, or use it in Image to Video.
The Image to Video style calls the main person “Image 1”, so the prompt works directly with your photo in Image to Video.
3 free prompts a day after sign-in.
Your prompt appears here
Subject, scene, action, camera, composition, light and sound — plus a prompt you can copy.
Video to Prompt
Automatic prompts from clips are not available yet. Write your scene description to use Image to Video now.
Image to Video
Use that prompt with your own photo to make a brand-new clip.
Questions about videos
How does Image to Video work?
Upload 1–4 photos, refer to them as Image 1 to Image 4 in your prompt, and the model generates a new 5–15 second clip with sound.
Can I replace someone in an existing video?
No. Image to Video only takes photos and text. It never swaps faces or edits existing footage.
How much does a video cost?
10 credits per second at 480p and 12 at 768p. A 5-second 768p clip is 60 credits.
Whose photos may I use?
Your own, or of adults who explicitly agreed. No celebrities, public figures, intimate or deceptive content.
Questions about prompts
What does Video to Prompt do?
Google Gemini watches your clip at two frames a second and writes a prompt describing the subject, scene, action, camera movement, composition, light and sound, plus a version ready for Image to Video and a short version.
Is it free?
This tool is completing verification and is not available yet. Planned free limits will be shown before use.
Does it identify the people in my video?
No. People are described by appearance and action only. Comparisons with known people are removed, and real public figures are refused.
Is my video used to make another video?
No. The clip is analysed into text and deleted; it is never sent to a video generation model.