You're looking at a specific version of this model. Jump to the model overview.

retro-diffusion /rd-plus:60eb48db

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
prompt
string
Text prompt for generation
style
None
default
Style to apply to the generated image default: Clean pixel art style with bold colors and outlines retro: Classic pixel art style inspired by PC98 games watercolor: Pixel art mixed with a watercolor painting aesthetic textured: Semi-realistic pixel art style with lots of shading and texture cartoon: Simple shapes and shading, with bold outlines ui_element: User interface boxes and buttons item_sheet: Sheets of objects placed on a simple background character_turnaround: Character sprites viewed from different angles environment: One-point perspective scenes with outlines and strong shapes isometric: 45 degree isometric perspective, with consistent outlines isometric_asset: 45 degree isometric objects or assets, on a neutral background topdown_map: Video game map style pixel art with a 3/4 top down perspective topdown_asset: 3/4 top down perspective game assets on a simple background classic: Strongly outlined medium-resolution pixel art with a focus on simple shading and clear design topdown_item: Small 3/4 top down perspective assets with no background low_res: High quality, low resolution pixel art assets and backgrounds mc_item: High quality Minecraft-styled items and game assets mc_texture: Detailed Minecraft-style flat block textures, with enhanced prompt following skill_icon: Video game style skill icons for representing abilities
width
integer
256

Min: 16

Max: 384

Image width
height
integer
256

Min: 16

Max: 384

Image height
num_images
integer
1

Min: 1

Max: 10

Number of images to generate
input_image
string
Input image for image-to-image generation or reference. Will be converted to RGB without transparency.
strength
number
0.8

Max: 1

Prompt strength in image-to-image generation. Higher values give closer adherence to the prompt, and lower values use more information from the input image. Only used when input_image is provided.
input_palette
string
Reference palette image to guide color choices
remove_bg
boolean
False
Remove background to create transparent images
tile_x
boolean
False
Enable seamless tiling on X axis
tile_y
boolean
False
Enable seamless tiling on Y axis
bypass_prompt_expansion
boolean
False
Disable automatic prompt expansion
seed
integer
Random seed. Set for reproducible generation

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'items': {'format': 'uri', 'type': 'string'},
 'title': 'Output',
 'type': 'array'}