Skip to main content

​
Overview

ByteDance’s advanced text-to-image modelgeneration
  • Output Type: image
  • Estimated Cost: 6 credits
  • Handler: replicate

​
Parameters

​
Required Parameters

​
prompt
string
required
Text prompt for image generation
  • Label: Prompt

​
Optional Parameters

​
size
string
default:"2K"
Image resolution preset
1K: 1024px, 2K: 2048px, 4K: 4096px, custom: use width/height parameters
  • Label: Size
  • Options: 1K, 2K, 4K, custom
​
width
integer
default:2048
Custom image width in pixels (only used when size is ‘custom’)
  • Label: Width
  • Minimum: 1024
  • Maximum: 4096
​
height
integer
default:2048
Custom image height in pixels (only used when size is ‘custom’)
  • Label: Height
  • Minimum: 1024
  • Maximum: 4096
​
aspect_ratio
string
default:"match_input_image"
Aspect ratio for the generated image
Set aspect ratio manually (not “match_input_image”) if you do not have any image inputs
  • Label: Aspect ratio
  • Options: match_input_image, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9
​
image_input
array<image>
Optional input image(s) to use as references
Optional input images for image-to-image transformation or object/style reference
  • Label: Input images
​
max_images
integer
default:1
Maximum number of images to generate when sequential generation is enabled
  • Label: Number of images
  • Minimum: 1
  • Maximum: 15
​
sequential_image_generation
string
default:"disabled"
Group image generation mode
When enabled, the model will generate a batch of up to max_images images with consistency
  • Label: Sequential generation
  • Options: disabled, auto
⌘I