Seedream 4.5
Seedream 4.5 is an image model by ByteDance. Use it to generate or revise a composed scene from a clear description and references. Keep the role of each source explicit; multiple images are not automatically a storyboard.
| Setting | Value |
|---|---|
| Model ID | seedream45 |
| Name | Seedream 4.5 |
| Availability | available |
| Default for new nodes | no |
Common declared limits
Section titled “Common declared limits”| Setting | Value |
|---|---|
| Capabilities | text to image, reference edit, multi reference |
| Controls | resolution: 1K, 1.5K, 2K; fallback 2K |
| Element input form | sheet |
| Maximum image references | 14 |
Limits apply together. initial is the studio choice for a new node; default is the fallback for an existing node without that value. Declared language or input support does not guarantee a successful result.
Prompting playbook
Section titled “Prompting playbook”Describe subject, action and setting in connected sentences. For an edit, name the object and explain what should remain. Quote any text that must appear in the image.
Studio example
Section titled “Studio example”On an Image node (Картинка), choose Seedream 4.5. Supply the input image or Element when the selected operation requires a reference. Use this original example as a starting point:
A paper lantern shop at dusk. Two unlit lanterns sit on a wooden counter; one warm lamp illuminates their paper texture. The sign above the counter reads “OPEN”.
Review the prompt and expected format before running. Compare the output against the source, including hands, face, object count, lettering and crop. Use the resulting scene image as a video first frame only after approving it. For automation, follow the supported MCP workflow.
Known failure modes
Section titled “Known failure modes”Check spelling, small objects and identity in every output. An author feature such as multi-image sequence generation is not automatically a dedicated sequence control in Vini.
Evidence and limits
Section titled “Evidence and limits”Current hero-input research records a character-sheet case without sheet layout leaking into the output. No general typography or maximum-reference benchmark is claimed.
An available reference input is not a guarantee of identity preservation. See reference workflows and image style samples. Generation and editing are different tasks; keep their evidence separate.
Reviewed 14 October 2026 against Vini’s image registry and dated research. Official model-author documentation checked on that date. Recheck the guidance when the model version or connected operation changes.