Which AI method fits what you want?
| You want to… | Method | What happens |
|---|---|---|
| Put yourself in a new scene | Reference-to-video (this site) | Your photos set the look; the scene, motion and sound are generated |
| Make one photo move | Image-to-video | The photo becomes the first frame and is animated |
| Create a scene with no specific person | Text-to-video | Everything comes from the prompt |
| Change who appears in an existing video | Not offered here | We never swap faces or replace people in footage |
What makes a good reference photo?
- One person per photo, with the face clearly visible.
- Even light and a sharp image; avoid heavy filters.
- Waist-up or full-body if the outfit matters.
- Two or three angles of the same person for a steadier look.
What can you make?
- Social clips: yourself travelling, dancing or reacting in a vertical 9:16 frame.
- Product and creator content: you presenting your own product in a styled set.
- Storyboards: try a scene idea before you film it.
- Greetings: a short festive clip of yourself, labelled as AI-generated.
How do you write the prompt?
Say who (Image 1), where, what they do, how the camera moves and what it sounds like, in one or two sentences. The guide has templates and settings. A 5-second 480p clip uses 50 credits on this site (full pricing).
Consent and disclosure
Use photos of yourself, or of adults who explicitly authorized this use, and hold the rights to them. Image to Video takes photos and text only, does not swap faces and does not replace people in existing footage. Impersonating anyone, public figures, fabricated statements or evidence, undressing and intimate scenes are prohibited even with permission. See our content policy. Label published results as AI-generated: YouTube requires creators to disclose realistic content made or meaningfully altered with AI, and other platforms have similar labelling rules.
FAQ
How do I turn a photo into a video with AI?
Use a reference-to-video model: upload a clear photo, describe the scene, action and camera, and choose a length. The model generates a new clip in which the pictured person is the subject.
Is photo to video the same as animating a photo?
Not quite. Image-to-video animates the photo itself as the first frame. Reference-to-video keeps the person's look and builds a completely new scene around them.
Which photos give the best result?
Sharp, evenly lit photos with the face clearly visible, one person per photo. Two or three angles of the same person often hold the likeness better than one.
Can I use photos of other people?
Only of adults who explicitly authorized it, and never of celebrities or public figures. Consent does not allow intimate, sexual or deceptive results.
Is this a face swap?
No. Nothing is pasted onto existing footage, and Image to Video takes photos and text only. The result is a new AI-generated clip and should be labelled as such.