Hugging Face's logo

GeroldMeisinger
/
control-edgedrawing

Transformers
English
controlnet
Inference Endpoints
Model card Files Community
Gerold Meisinger commited on
Commit
0b3513f
•
1 Parent(s): be8d5ad

blub

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -10,36 +10,33 @@ Based on my GitHub monologs at [Edge Drawing - a Canny alternative](https://gith
10
 
11
  Controls image generation by edge maps generated with [EdgeDrawing Parameter-Free](https://github.com/CihanTopal/ED_Lib).
12
 
13
- For usage see the model page on [Civitai.com]().
14
-
15
- # Image dataset
16
-
17
- * [laion2B-en aesthetics>=6.5 dataset](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus)
18
- * `--min_image_size 512 --max_aspect_ratio 2 --resize_mode="center_crop" --image_size 512`
19
- * resulting in 180k images
20
-
21
- Original
22
 
 
23
 
24
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/RgXLEFqwSOzYQXvrs6pOr.png)
25
 
26
- EdgeDrawing Parameter-Free
27
-
28
 
29
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/jmdCGeMJx4dKFGo44cuEq.png)
30
 
31
- Canndy Edge Detection (default in Automatic1111)
32
-
33
 
34
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/JZTpa-HZfw0NUYnxZ52Iu.png)
35
 
36
- Example
 
37
  sampler=UniPC steps=20 cfg=7.5 seed=0 batch=9 model: v1-5-pruned-emaonly.safetensors cherry-picked: 1/9
38
  prompt: _a detailed high-quality professional photo of swedish woman standing in front of a mirror, dark brown hair, white hat with purple feather_
39
 
40
-
41
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/2PSWsmzLdHeVG-i67S7jF.png)
42
 
 
 
 
 
 
 
43
  # Training
44
 
45
  ```
@@ -106,3 +103,8 @@ Update: bug in algorithm produces too sparse images on default, see https://gith
106
  additional arguments: `--proportion_empty_prompts=0.5`
107
  Trained for 40000 steps with default settings
108
  => empty prompts were probably too excessive
 
 
 
 
 
 
10
 
11
  Controls image generation by edge maps generated with [EdgeDrawing Parameter-Free](https://github.com/CihanTopal/ED_Lib).
12
 
13
+ For usage see the model page on [Civitai.com](https://civitai.com/models/149740).
 
 
 
 
 
 
 
 
14
 
15
+ **Original**
16
 
17
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/RgXLEFqwSOzYQXvrs6pOr.png)
18
 
19
+ **EdgeDrawing Parameter-Free**
 
20
 
21
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/jmdCGeMJx4dKFGo44cuEq.png)
22
 
23
+ **Canndy Edge Detection (default in Automatic1111)**
 
24
 
25
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/JZTpa-HZfw0NUYnxZ52Iu.png)
26
 
27
+ **Example**
28
+
29
  sampler=UniPC steps=20 cfg=7.5 seed=0 batch=9 model: v1-5-pruned-emaonly.safetensors cherry-picked: 1/9
30
  prompt: _a detailed high-quality professional photo of swedish woman standing in front of a mirror, dark brown hair, white hat with purple feather_
31
 
 
32
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c0ec65a2ec8cb2f589233a/2PSWsmzLdHeVG-i67S7jF.png)
33
 
34
+ # Image dataset
35
+
36
+ * [laion2B-en aesthetics>=6.5 dataset](https://huggingface.co/datasets/ChristophSchuhmann/improved_aesthetics_6.5plus)
37
+ * `--min_image_size 512 --max_aspect_ratio 2 --resize_mode="center_crop" --image_size 512`
38
+ * resulting in 180k images
39
+
40
  # Training
41
 
42
  ```
 
103
  additional arguments: `--proportion_empty_prompts=0.5`
104
  Trained for 40000 steps with default settings
105
  => empty prompts were probably too excessive
106
+
107
+ # Question and answers
108
+
109
+ **Q: What's the point of another edge control net anyway?**
110
+ A: 🤷