brad-twinkl commited on
Commit
811781b
·
verified ·
1 Parent(s): 5109f7d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -192
README.md CHANGED
@@ -10,195 +10,5 @@ pipeline_tag: text-to-image
10
 
11
  # **ControlNet++: All-in-one ControlNet for image generations and editing!**
12
  ## **ProMax Model has released!! 12 control + 5 advanced editing, just try it!!!**
13
- ![images_display](./images/masonry.webp)
14
-
15
- ## Network Arichitecture
16
- ![images](./images/ControlNet++.png)
17
-
18
- ## Advantages about the model
19
- - Use bucket training like novelai, can generate high resolutions images of any aspect ratio
20
- - Use large amount of high quality data(over 10000000 images), the dataset covers a diversity of situation
21
- - Use re-captioned prompt like DALLE.3, use CogVLM to generate detailed description, good prompt following ability
22
- - Use many useful tricks during training. Including but not limited to date augmentation, mutiple loss, multi resolution
23
- - Use almost the same parameter compared with original ControlNet. No obvious increase in network parameter or computation.
24
- - Support 10+ control conditions, no obvious performance drop on any single condition compared with training independently
25
- - Support multi condition generation, condition fusion is learned during training. No need to set hyperparameter or design prompts.
26
- - Compatible with other opensource SDXL models, such as BluePencilXL, CounterfeitXL. Compatible with other Lora models.
27
-
28
-
29
- ***We design a new architecture that can support 10+ control types in condition text-to-image generation and can generate high resolution images visually comparable with
30
- midjourney***. The network is based on the original ControlNet architecture, we propose two new modules to: 1 Extend the original ControlNet to support different image
31
- conditions using the same network parameter. 2 Support multiple conditions input without increasing computation offload, which is especially important for designers
32
- who want to edit image in detail, different conditions use the same condition encoder, without adding extra computations or parameters. We do thoroughly experiments
33
- on SDXL and achieve superior performance both in control ability and aesthetic score. We release the method and the model to the open source community to make everyone
34
- can enjoy it.
35
-
36
- Inference scripts and more details can found: https://github.com/xinsir6/ControlNetPlus/tree/main
37
-
38
- **If you find it useful, please give me a star, thank you very much**
39
-
40
- **~500+ star, release the ProMax version with tile and inpainting!!!~**
41
- **SDXL ProMax version has been released!!!,Enjoy it!!!**
42
- **1000+ star, release the ControlNet++ model for SD3!!!**
43
- **3000+ star, release the ControlNet++ ProMax model for SD3!!!**
44
-
45
- Note: we put the promax model with a promax suffix in the same [huggingface model repo](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0), detailed instructions will be added later.
46
- ## Advanced editing features in Promax Model
47
- ### Tile Deblur
48
- ![blur0](./images/100000_tile_blur_concat.webp)
49
- ![blur1](./images/100001_tile_blur_concat.webp)
50
- ![blur2](./images/100002_tile_blur_concat.webp)
51
- ![blur3](./images/100003_tile_blur_concat.webp)
52
- ![blur4](./images/100004_tile_blur_concat.webp)
53
- ![blur5](./images/100005_tile_blur_concat.webp)
54
- ### Tile variation
55
- ![var0](./images/100006_tile_var_concat.webp)
56
- ![var1](./images/100007_tile_var_concat.webp)
57
- ![var2](./images/100008_tile_var_concat.webp)
58
- ![var3](./images/100009_tile_var_concat.webp)
59
- ![var4](./images/100010_tile_var_concat.webp)
60
- ![var5](./images/100011_tile_var_concat.webp)
61
-
62
- ### Tile Super Resolution
63
- Following example show from 1M resolution --> 9M resolution
64
- <div style="display: flex; justify-content: space-between;">
65
- <img src="./images/tile_super1.webp" alt="Image 1" style="width: 49%; margin: 1%;">
66
- <img src="./images/tile_super1_9upscale.webp" alt="Image 2" style="width: 49%; margin: 1%;">
67
- </div>
68
-
69
- <div style="display: flex; justify-content: space-between;">
70
- <img src="./images/tile_super2.webp" alt="Image 1" style="width: 49%; margin: 1%;">
71
- <img src="./images/tile_super2_9upscale.webp" alt="Image 2" style="width: 49%; margin: 1%;">
72
- </div>
73
-
74
- ### Image Inpainting
75
- ![inp0](./images/100018_inpainting_concat.webp)
76
- ![inp1](./images/100019_inpainting_concat.webp)
77
- ![inp2](./images/100020_inpainting_concat.webp)
78
- ![inp3](./images/100021_inpainting_concat.webp)
79
- ![inp4](./images/100022_inpainting_concat.webp)
80
- ![inp5](./images/100023_inpainting_concat.webp)
81
-
82
- ### Image Outpainting
83
- ![oup0](./images/100012_outpainting_concat.webp)
84
- ![oup1](./images/100013_outpainting_concat.webp)
85
- ![oup2](./images/100014_outpainting_concat.webp)
86
- ![oup3](./images/100015_outpainting_concat.webp)
87
- ![oup4](./images/100016_outpainting_concat.webp)
88
- ![oup5](./images/100017_outpainting_concat.webp)
89
-
90
-
91
- ## Visual Examples
92
- ### Openpose
93
- ![pose0](./images/000000_pose_concat.webp)
94
- ![pose1](./images/000001_pose_concat.webp)
95
- ![pose2](./images/000002_pose_concat.webp)
96
- ![pose3](./images/000003_pose_concat.webp)
97
- ![pose4](./images/000004_pose_concat.webp)
98
- ### Depth
99
- ![depth0](./images/000005_depth_concat.webp)
100
- ![depth1](./images/000006_depth_concat.webp)
101
- ![depth2](./images/000007_depth_concat.webp)
102
- ![depth3](./images/000008_depth_concat.webp)
103
- ![depth4](./images/000009_depth_concat.webp)
104
- ### Canny
105
- ![canny0](./images/000010_canny_concat.webp)
106
- ![canny1](./images/000011_canny_concat.webp)
107
- ![canny2](./images/000012_canny_concat.webp)
108
- ![canny3](./images/000013_canny_concat.webp)
109
- ![canny4](./images/000014_canny_concat.webp)
110
- ### Lineart
111
- ![lineart0](./images/000015_lineart_concat.webp)
112
- ![lineart1](./images/000016_lineart_concat.webp)
113
- ![lineart2](./images/000017_lineart_concat.webp)
114
- ![lineart3](./images/000018_lineart_concat.webp)
115
- ![lineart4](./images/000019_lineart_concat.webp)
116
- ### AnimeLineart
117
- ![animelineart0](./images/000020_anime_lineart_concat.webp)
118
- ![animelineart1](./images/000021_anime_lineart_concat.webp)
119
- ![animelineart2](./images/000022_anime_lineart_concat.webp)
120
- ![animelineart3](./images/000023_anime_lineart_concat.webp)
121
- ![animelineart4](./images/000024_anime_lineart_concat.webp)
122
- ### Mlsd
123
- ![mlsd0](./images/000025_mlsd_concat.webp)
124
- ![mlsd1](./images/000026_mlsd_concat.webp)
125
- ![mlsd2](./images/000027_mlsd_concat.webp)
126
- ![mlsd3](./images/000028_mlsd_concat.webp)
127
- ![mlsd4](./images/000029_mlsd_concat.webp)
128
- ### Scribble
129
- ![scribble0](./images/000030_scribble_concat.webp)
130
- ![scribble1](./images/000031_scribble_concat.webp)
131
- ![scribble2](./images/000032_scribble_concat.webp)
132
- ![scribble3](./images/000033_scribble_concat.webp)
133
- ![scribble4](./images/000034_scribble_concat.webp)
134
- ### Hed
135
- ![hed0](./images/000035_hed_concat.webp)
136
- ![hed1](./images/000036_hed_concat.webp)
137
- ![hed2](./images/000037_hed_concat.webp)
138
- ![hed3](./images/000038_hed_concat.webp)
139
- ![hed4](./images/000039_hed_concat.webp)
140
- ### Pidi(Softedge)
141
- ![pidi0](./images/000040_softedge_concat.webp)
142
- ![pidi1](./images/000041_softedge_concat.webp)
143
- ![pidi2](./images/000042_softedge_concat.webp)
144
- ![pidi3](./images/000043_softedge_concat.webp)
145
- ![pidi4](./images/000044_softedge_concat.webp)
146
- ### Teed
147
- ![ted0](./images/000045_ted_concat.webp)
148
- ![ted1](./images/000046_ted_concat.webp)
149
- ![ted2](./images/000047_ted_concat.webp)
150
- ![ted3](./images/000048_ted_concat.webp)
151
- ![ted4](./images/000049_ted_concat.webp)
152
- ### Segment
153
- ![segment0](./images/000050_seg_concat.webp)
154
- ![segment1](./images/000051_seg_concat.webp)
155
- ![segment2](./images/000052_seg_concat.webp)
156
- ![segment3](./images/000053_seg_concat.webp)
157
- ![segment4](./images/000054_seg_concat.webp)
158
- ### Normal
159
- ![normal0](./images/000055_normal_concat.webp)
160
- ![normal1](./images/000056_normal_concat.webp)
161
- ![normal2](./images/000057_normal_concat.webp)
162
- ![normal3](./images/000058_normal_concat.webp)
163
- ![normal4](./images/000059_normal_concat.webp)
164
-
165
- ## Multi Control Visual Examples
166
- ### Openpose + Canny
167
- ![pose_canny0](./images/000007_openpose_canny_concat.webp)
168
- ![pose_canny1](./images/000008_openpose_canny_concat.webp)
169
- ![pose_canny2](./images/000009_openpose_canny_concat.webp)
170
- ![pose_canny3](./images/000010_openpose_canny_concat.webp)
171
- ![pose_canny4](./images/000011_openpose_canny_concat.webp)
172
- ![pose_canny5](./images/000012_openpose_canny_concat.webp)
173
-
174
- ### Openpose + Depth
175
- ![pose_depth0](./images/000013_openpose_depth_concat.webp)
176
- ![pose_depth1](./images/000014_openpose_depth_concat.webp)
177
- ![pose_depth2](./images/000015_openpose_depth_concat.webp)
178
- ![pose_depth3](./images/000016_openpose_depth_concat.webp)
179
- ![pose_depth4](./images/000017_openpose_depth_concat.webp)
180
- ![pose_depth5](./images/000018_openpose_depth_concat.webp)
181
-
182
- ### Openpose + Scribble
183
- ![pose_scribble0](./images/000001_openpose_scribble_concat.webp)
184
- ![pose_scribble1](./images/000002_openpose_scribble_concat.webp)
185
- ![pose_scribble2](./images/000003_openpose_scribble_concat.webp)
186
- ![pose_scribble3](./images/000004_openpose_scribble_concat.webp)
187
- ![pose_scribble4](./images/000005_openpose_scribble_concat.webp)
188
- ![pose_scribble5](./images/000006_openpose_scribble_concat.webp)
189
-
190
- ### Openpose + Normal
191
- ![pose_normal0](./images/000019_openpose_normal_concat.webp)
192
- ![pose_normal1](./images/000020_openpose_normal_concat.webp)
193
- ![pose_normal2](./images/000021_openpose_normal_concat.webp)
194
- ![pose_normal3](./images/000022_openpose_normal_concat.webp)
195
- ![pose_normal4](./images/000023_openpose_normal_concat.webp)
196
- ![pose_normal5](./images/000024_openpose_normal_concat.webp)
197
-
198
- ### Openpose + Segment
199
- ![pose_segment0](./images/000025_openpose_sam_concat.webp)
200
- ![pose_segment1](./images/000026_openpose_sam_concat.webp)
201
- ![pose_segment2](./images/000027_openpose_sam_concat.webp)
202
- ![pose_segment3](./images/000028_openpose_sam_concat.webp)
203
- ![pose_segment4](./images/000029_openpose_sam_concat.webp)
204
- ![pose_segment5](./images/000030_openpose_sam_concat.webp)
 
10
 
11
  # **ControlNet++: All-in-one ControlNet for image generations and editing!**
12
  ## **ProMax Model has released!! 12 control + 5 advanced editing, just try it!!!**
13
+ This is just a copy of the original repo [here](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0) by xinsir.
14
+ The only difference is I have renamed the Promax model to make it easier to use.