Skip to main content
Endpoint: POST https://fal.run/fal-ai/bytedance/seedream/v3/text-to-image Endpoint ID: fal-ai/bytedance/seedream/v3/text-to-image

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

Input Schema

string
required
The text prompt used to generate the image
ImageSize | Enum
Use for finer control over the output image size. Will be used over aspect_ratio, if both are provided. Width and height must be between 512 and 2048.Possible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
float
default:"2.5"
Controls how closely the output image aligns with the input prompt. Higher values mean stronger prompt correlation. Default value: 2.5Range: 1 to 10
integer
default:"1"
Number of images to generate Default value: 1Range: 1 to 4
integer
Random seed to control the stochasticity of image generation.
boolean
default:"true"
If set to true, the safety checker will be enabled. Default value: true
boolean
default:"false"
If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Output Schema

list<Image>
required
Generated images
integer
required
Seed used for generation

Input Example

Output Example

Limitations

  • image_size restricted to: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
  • guidance_scale range: 1 to 10
  • num_images range: 1 to 4
  • Content moderation via safety checker