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

nsfw-api /joycaption-beta-one:4a99d942

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
image_zip
string
Input ZIP file containing images to caption
prompt
string
Write a long descriptive caption for this image in a formal tone.
Prompt to guide the captioning (e.g., 'Write a detailed caption for this image')
max_new_tokens
integer
512
Maximum number of tokens to generate
temperature
number
0.6

Min: 0.1

Max: 2

Sampling temperature (higher = more random)
top_p
number
0.9

Max: 1

Top-p sampling (nucleus sampling)
internal_batch_size
integer
4

Min: 1

Number of images to process in a single internal GPU batch. Adjust based on VRAM.

Output schema

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

Schema
{'title': 'Output', 'type': 'string'}