Which AI video tools make an avatar from a photo?

Five tools' pages describe it: D-ID's photo avatars come from a single image, Topview's talking avatars from one photo and a script, Vyond's characters from an uploaded or taken photo, Descript's avatars from a photo, a prompt or the stock gallery, and Google Flow's avatar from your own likeness. From 5 source pages, read 2026-09-25; no maker pays to be listed.

Inclusion rule. A tool is listed when its own help page covers what the question asks. Order. Tools in alphabetical order.

A photo avatar is the quickest way to put one recognisable face through a whole series, because the face is fixed before the first scene is made.

The pages differ in what the photo becomes: a talking head at D-ID and Topview, an animated character at Vyond, a presenter at Descript.

Google Flow's page is about an avatar of the user rather than a character, and it notes that the avatar cannot be shared through public project links.

1In the pages' own words

D-ID

V2 Avatars, also known as Photo Avatars, are created from a single image using lightweight rendering, enabling fast generation while supporting a wide range of languages.

D-ID Help Center

Descript

Create a Descript avatar from a text prompt, a photo, or the stock gallery.

Descript Help Center

Google Flow

Securely create an avatar in Google Flow, featuring your own highly accurate visual and audio likeness.

Google Flow Help

Topview

Create hyper-realistic AI avatars for product promotion, keynote speeches, storytelling, and more — all from a single photo and a script.

Topview official guides

Vyond

Photo to character allows users to either upload a photo or take a photo to generate a character.

Vyond Help Center

• What are V2 Avatars?
  Photo avatars made from a single imageD-ID Help Center / recorded 2026-09-25
• Create your avatar
  An on-screen avatar made from a text prompt, a photo or the stock galleryDescript Help Center / recorded 2026-09-25
• Create & use your avatar in Google Flow
  An avatar of yourself, with your own visual and audio likenessGoogle Flow Help / recorded 2026-09-25
• Topview Official Guide: AI Avatar
  Talking avatars built from one photo and a scriptTopview official guides / recorded 2026-09-25
• Photo to Character Tips
  A character generated from an uploaded photo, then edited in the Character CreatorVyond Help Center / recorded 2026-09-25

Keeping characters the same, every tool · Which AI video tools edit through a chat assistant? · How do AI video tools divide a video into scenes?

2A generator's own guide on this

Set beside “Which AI video tools make an avatar from a photo?”, two passages from the guides SceneMixer publishes about its own pipeline:

SceneMixer turns a novel into a watchable short-drama series in one pipeline: upload the novel (Chinese or English) → AI extracts characters, scenes, and an episode-by-episode structure → generates consistent character and scene art → writes storyboard scripts → renders video segment by segment (16:9 by default, 9:16 in one setting) → composites full episodes.

SceneMixer, Turn a Novel into a Video Series with AI (read 2026-10-13)

The same way as a photographic one: the character is generated once as a reference sheet and that image is sent with every shot they are in, along with a couple of face-distinguishing notes. Shots refer to the character rather than re-describing their look.

SceneMixer, AI Animated Series Generator — “How do I keep a stylised character on model across episodes?” (read 2026-10-13)