ai_diffusion
An authenticated client can post a request to Stable Diffusion v1.4
Last updated
An authenticated client can post a request to Stable Diffusion v1.4
Last updated
Stable Diffusion comes with two flavors to produce images:
TXT2IMG: a text to image generation AI. Input text and a few additional parameters.
IMG2IMG: an image to image generation AI. Input a guiding image (full URI of the image), additional text, and a few additional parameters
GET
https://opensourceais.com/api/v1/public/config/diffusion
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/diffusion
Name | Type | Description |
---|---|---|
width | Number | The width of the output image. Defaults to 320 |
height | Number | The height of the output image. Defaults to 320 |
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 200. |
seed | Number | A random number between 1 and 1,000,000 used by the TXT2IMG generation. Same seed and exact same params delivers same output. Defaults to 1. 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 1, corresponding to a % of strength applied for the IMG2IMG generation. Defaults to 0.75. |
guidance | Float | A float between 0.1 and 10, corresponding to the guidance scale applied for the TXT2IMG generation. Defaults to 7.5. |
cimg | Number | The number of images to produce. Defaults to 1. Note that more images to produce will cost proportionally more in GPU compute. |