Seedream Models by ByteDance
ByteDanceProprietary
2 models2025
Last refreshed 2026-07-10. Next refresh: weekly.
Details
ResearcherByteDance
LicenseProprietary
Commercial useCommercial use: conditional
Models2
Released2025
Capabilities
MultimodalAll models
Links
WebsiteAbout
ByteDance's Seedream family of text-to-image generation models from the Seed team. Part of ByteDance's AI research portfolio alongside Doubao.
Decision facts
- Best fit
- image generationvision and multimodal work
- Capability starting point
- Seedream 4.5 with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- BAGEL
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
Seedream 4.5Current
Use when the workload needs image generation and multimodal inputs.
2025-12image generationmultimodal inputs
Seedream v5Current
Use when the workload needs image generation and multimodal inputs.
2025-03image generationmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Seedream 4.5 | Use when the workload needs image generation and multimodal inputs. | 2025-12 | image generationmultimodal inputs | Current |
| Seedream v5 | Use when the workload needs image generation and multimodal inputs. | 2025-03 | image generationmultimodal inputs | Current |
Release Timeline
2 release groups2025-12
1 current
Seedream 4.5
Currentimage generationmultimodal inputs
2025-03
1 current
Seedream v5
Currentimage generationmultimodal inputs
Specifications(2 models)
| Model | Released | Multimodal |
|---|---|---|
| Seedream 4.5 | 2025-12 | Yes |
| Seedream v5 | 2025-03 | Yes |
