tags:
- text-to-image
- stable-diffusion
Control-LoRA Model Card
Model
This is the place where we're gonna talk about how amazing this new thing is, and how it's gonna change the world, and how we're so proud of what we've done, and how everyone who HASN'T done this exactly this way is probably mean to servers when they go to restaurants (which is a huge red, imho)
MiDaS and ClipDrop Depth
Canny Edge
Canny Edge Detection is an image processing technique that identifies abrupt changes in intensity to highlight edges in an image.
This Control-LoRA uses the edges from an image to guide the generation.
Photograph and Sketch Colorizer
These two Control-LoRAs can be used to colorize images.
The first is designed to colorize black and white photographs.
The second is designed to color in sketches input as a white-on-black image (either hand-drawn, or created with a SoftEdge_PIDI model).
Revision
Revision is a novel approach of using images to prompt SDXL.
It uses pooled CLIP embeddings to produce images conceptually similar to the input. It can be used either in addition, or to replace text prompts.
Revision also includes a blending function for combining multiple image or text concepts, as either positive or negative prompts.