ai_cnet
An authenticated client can post a request to Control Net v1.1
Last updated
An authenticated client can post a request to Control Net v1.1
Last updated
This Control Net AI works on top of Stable Diffusion v1.5 which is bundled into it. Control Net requires an image in input, as such is is an IMG2IMG AI. Its parameters add on top of the Stable Diffusion v1.5 parameters.
This AI can run AI alongside a Daemon on GPU only
GET
https://opensourceais.com/api/v1/public/config/cnet
You should not need to call this endpoint. This is just a FYI to understand all input parameters sent to the AI.
POST
https://opensourceais.com/api/v1/private/client/ai/cnet
Name | Type | Description |
---|---|---|
res
Number
The resolution of the output image. Defaults to 512 (for 512x512)
steps
Number
The number of steps requested for generating the output image. High number of steps cost more GPU compute. Defaults to 20. Should not exceed 100.
seed
Number
A random number between 1 and
2,147,483,647. Same seed and exact same params delivers same output. Defaults to 12345. Should send random values for better experience.
word*
String
A text input to tell the AI what to generate.
url_upload
String
A well formed URI starting with https://... and accessing a PNG or JPG image. Note that if the image is not of the width and height size passed in parameters, it will be automatically cropped or resized.
strength
Float
A float between 0 and 2, corresponding to a % of strength applied. Defaults to 1.
guidance
Float
A float between 0.1 and 30, corresponding to the guidance scale applied. Defaults to 9.
cimg
Number
The number of images to produce. Defaults to 1. Note that more images to produce will cost proportionally more in GPU compute.