Seedream 3.0

ByteDance's bilingual (Chinese/English) foundation image model with native 2K output and no post-processing: better structural accuracy, small-text rendering and layout, stronger portraits and aesthetics, with 1K images in about 3 seconds.

Техотчёт опубликован 16.04.2025; вендор пишет, что модель уже работает в Doubao и Jimeng.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

images

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.