Anam Cara-4 anime and 3D avatar images vs Sume's photo input

Sume's avatar docs do not list anime or 3D characters as supported or unsupported. They describe three input kinds and one URL rule, and nothing about art style. So try your image, and read the job result before you build on it.

Anam facts are from its Cara-4 post; Sume facts from Create new avatar, read 2026-10-01.

What does Anam claim?

Custom avatars no longer need to come from a conventional photo: Cara-4 can animate a wider range of images, including animated 3D characters or anime.

What does Sume accept as input?

On POST /v1/avatar-1.0/generate the input union is a prompt, a props profile, or a photo with image_url. The image_url must be a fetchable public HTTPS image URL. Localhost, private-network, non-HTTPS and non-image responses are rejected before generation. The handle may include a leading @; Sume stores it normalized without @.

How do I test a cartoon image?

Create the avatar with the photo input, poll the job, and look at the result before spending on a long script. For a cartoon-style talking clip, see AI talking cartoon character from image.