Skip to main content
Seedream 5.0 Lite is ByteDance’s latest image creation model. It supports text prompts, single-image references, and multi-image inputs, and can generate image sets in a single request. The model introduces web search grounding for more up-to-date image generation and improves instruction understanding, visual analysis, world knowledge coverage, reference consistency, and quality in professional production scenarios. It is positioned as a capable general-purpose image model for both text-to-image and image-to-image workflows while maintaining a simple per-image pricing model.

​
Model ID

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

​
Supported modes

  • image_generation
  • image_reference

​
Inputs

  • Text
  • Image

​
Outputs

  • Image

​
Capabilities

  • Image-to-image
  • Text-to-image

​
Additional capabilities

  • Model experience

​
Technical details

Availability and final customer prices can change. Check the Dashboard model catalog before production use.
See the API reference overview for authentication, request conventions, and response schemas.