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

afiaka87 /retrieval-augmented-diffusion:ac7878df

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
prompts
string
(batched) Use up to 8 prompts by separating with a `|` character.
image_prompt
string
(overrides `prompts`) Use an image as the prompt to generate variations of an existing image.
number_of_variations
integer
4

Min: 1

Max: 8

Number of variations to generate when using only one `text_prompt`, or an `image_prompt`.
database_name
string (enum)
laion-aesthetic

Options:

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

Which database to use for the semantic search. Different databases have different capabilities.
use_database
boolean
True
Whether to use the database for the semantic search.
scale
number
5
Classifier-free unconditional scale for the sampler.
num_database_results
integer
10

Min: 1

Max: 20

The number of search results from the retrieval backend to guide the generation with.
height
integer
768
Desired width of generated images. Values beside 768 are likely to cause zooming issues.
width
integer
768
Desired width of generated images. Values beside 768 are not supported, likely to cause artifacts.
steps
integer
50
How many steps to run the model for. Using more will make generation take longer. 50 tends to work well.
ddim_sampling
boolean
False
Use ddim sampling instead of the faster plms sampling.
ddim_eta
number
0
The eta parameter for ddim sampling.
negative_prompt
string
(experimental) Use this prompt as a negative prompt for the sampler.
seed
integer
-1
Seed for the random number generator. Set to -1 to use a random seed.

Output schema

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

Schema
{'items': {'properties': {'caption': {'title': 'Caption', 'type': 'string'},
                          'image': {'format': 'uri',
                                    'title': 'Image',
                                    'type': 'string'}},
           'required': ['image', 'caption'],
           'title': 'CaptionedImage',
           'type': 'object'},
 'title': 'Output',
 'type': 'array'}