Overview
Unified text-to-image and editing, using a vision-language model for world knowledge and supporting up to 4K.
Seedream 4.0
Unified text-to-image and editing, using a vision-language model for world knowledge and supporting up to 4K.
MODEL NUMBER148
- Release date
- 2025-09-09
- Organization
- ByteDance Seed
- Family
- Seedream
01
Specifications
Only published specifications are shown.
02
Overview
03
Architecture & capabilities
Key capabilities
Image editingVisual reasoningHigh resolutionMulti-reference
04
Release history
Seedream 4.0 launched.
View source05
Related models
Select a card to view the related model.
06