Commit
·
8799257
1
Parent(s):
a27f73c
Update README.md
Browse files
README.md
CHANGED
@@ -11,13 +11,26 @@ tags:
|
|
11 |
<!-- Description -->
|
12 |
|
13 |
### Canny Edge
|
14 |
-
|
|
|
|
|
|
|
15 |
|
16 |
### MiDaS and ClipDrop Depth
|
17 |
-
|
18 |
|
19 |
### Photograph and Sketch Colorizer
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
### Revision
|
23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
11 |
<!-- Description -->
|
12 |
|
13 |
### Canny Edge
|
14 |
+

|
15 |
+
Canny Edge Detection is an image processing technique that identifies abrupt changes in intensity to highlight edges in an image.
|
16 |
+
|
17 |
+
This Control-LoRA uses the edges from an image to guide the generation.
|
18 |
|
19 |
### MiDaS and ClipDrop Depth
|
20 |
+

|
21 |
|
22 |
### Photograph and Sketch Colorizer
|
23 |
+
 
|
24 |
+
These two Control-LoRAs can be used to colorize images.
|
25 |
+
|
26 |
+
The first is designed to colorize black and white photographs.
|
27 |
+
|
28 |
+
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).
|
29 |
|
30 |
### Revision
|
31 |
+

|
32 |
+
Revision is a novel approach of using images to prompt SDXL.
|
33 |
+
|
34 |
+
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.
|
35 |
+
|
36 |
+
Revision also includes a blending function for combining multiple image or text concepts, as either positive or negative prompts.
|