Skip to content
Katechon Arc
Start creating
Menu

ANSWER

How do you make an AI video from photos?

Short answer

Upload a photo to an image-to-video model and describe the motion you want; the photo becomes the first frame or a reference. For a story with several shots, use the photos as references for every shot instead, so people and places stay the same across the video.

Two ways to use a photo

First frame versus reference
MethodWhat the photo doesBest for
Image to video (first frame)The clip starts exactly on your photo and animates itOne shot: a portrait coming alive, a product spin
Reference to videoThe model sees the photo as the look of a person, product or place and generates new shots of itSeveral shots or a story with the same subject

Veo 3.1 supports first-and-last-frame generation and up to three reference images. Source: Google AI for Developers, Veo 3.1 documentation (ai.google.dev/gemini-api/docs/veo), checked 2026-10-18

Seedance 2.0 accepts text, image, audio and video inputs, and supports images, audio and videos as references. Source: ByteDance Seed, Seedance 2.0 (seed.bytedance.com/en/seedance2_0), checked 2026-10-18

Model prices on this page are Atlas Cloud list prices quoted 2026-10-17 with its free /calculate endpoint, as published in our AI video price index. Source: Atlas Cloud model catalog and /calculate list prices (atlascloud.ai/models), checked 2026-10-17

Step by step for a short story from photos

  1. Pick clear photos of each person and place, one subject per photo.
  2. Turn each into a reference; for people, a clean sheet with the face visible.
  3. Write three to six shots, one action each.
  4. Generate each shot with its references attached and check it.
  5. Join the clips, add music or voice, export.

Rules worth knowing

  • Only use photos you have the rights to, and never animate a real person without their consent.
  • Faces that resemble famous actors can trigger copyright or likeness blocks on some models; we have had shots blocked for a character who looked like a well-known actor.
  • Realistic AI video of real-looking people may need an AI label when you publish.

Where Katechon Arc fits

Arc turns images into references for characters, locations, props and products and generates multi-shot stories from them in 9:16 or 16:9.

Arc is not a one-tap photo animator and has no free plan; for animating a single photo, an image-to-video app is quicker.

People also ask

What is the best image-to-video AI?

For one shot from one photo, most current models do it well; compare price per second and motion quality. For many shots of the same subject, choose a tool that uses the photo as a reusable reference.

Related answers

Text-to-video, image-to-video or reference-to-video: which should you use for a film?For a film with recurring characters, use reference-to-video or image-to-video, not plain text-to-video.How do you make an AI product video from product photos?Use the photos as reference images, not as the first frame only: shoot the product on a plain background from three or four angles, attach…How do you keep the same character across AI video clips?Give the model the same visual evidence every time: one approved reference image per character, attached to every shot that character is…Why do AI video generations fail or get blocked?Three different things look like a failure: transient job errors that pass on retry, content moderation that blocks an input or an output,…What is the cheapest AI video generator?By list price per second, the cheapest model we track is Veo 3.1 Lite at $0.050 per second at 720p (2026-10-17), followed by PixVerse V6…

Sources