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

afiaka87 /retrieval-augmented-diffusion:faf87c8c

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
model will try to generate this text.
database_name
string (enum)
laion-aesthetic

Options:

prompt-engineer, cars, openimages, faces, simulacra, coco, pixelart, food, country211, laion-aesthetic, vaporwave, pets, emotes, pokemon

Which database to use for the semantic search. Different databases have different capabilities.
prompt_scale
number
5
Determines influence of your prompt on generation.
num_database_results
integer
10

Min: 1

Max: 20

The number of search results to guide the generation with. Using more will 'broaden' capabilities of the model at the risk of causing mode collapse or artifacting.
num_generations
integer
1
Number of images to generate. Using more will make generation take longer.
height
integer
768
Desired height of generated images.
width
integer
768
Desired width of generated images.
steps
integer
50
How many steps to run the model for. Using more will make generation take longer. 50 tends to work well.

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'}