13-Stable Cascade

Stable cascade is a 3 stage process, first a low resolution latent image is generated with the Stage C diffusion model. This latent is then upscaled using the Stage B diffusion model. This upscaled latent is then upscaled again and converted to pixel space by the Stage A VAE.

Note that you can download all images in this page and then drag or load them on ComfyUI to get the workflow embedded in the image.

Text to Image

Here is a basic text to image workflow:

Image to Image

Here’s an example of how to do basic image to image by encoding the image and passing it to Stage C.

Image Variations

Stable Cascade supports creating variations of images using the output of CLIP vision. See the following workflow for an example:

See this next workflow for how to mix multiple images together:

ControlNet

Here is an example for how to use the Canny Controlnet:

Here is an example for how to use the Inpaint Controlnet, the example input image can be found here. A reminder that you can right click images in the LoadImage node and edit them with the mask editor.