patrickvonplaten williamberman commited on
Commit
29c13b4
1 Parent(s): c0e41c6

update README (#1)

Browse files

- update README (32a7d8203498f07503f555d269af13e51e8069b3)


Co-authored-by: Will Berman <williamberman@users.noreply.huggingface.co>

README.md CHANGED
@@ -18,107 +18,23 @@ Controlnet's auxiliary models are trained with stable diffusion 1.5. Experimenta
18
  The auxiliary conditioning is passed directly to the diffusers pipeline. If you want to process an image to create the auxiliary conditioning, external dependencies are required.
19
 
20
  Some of the additional conditionings can be extracted from images via additional models. We extracted these
21
- additional models from the original controlnet repo into a separate package that can be found on [github](https://github.com/patrickvonplaten/human_pose.git).
22
-
23
- ## Canny edge detection
24
-
25
- Install opencv
26
-
27
- ```sh
28
- $ pip install opencv-contrib-python
29
- ```
30
-
31
- ```python
32
- import cv2
33
- from PIL import Image
34
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
35
- import torch
36
- import numpy as np
37
-
38
- image = Image.open('images/bird.png')
39
- image = np.array(image)
40
-
41
- low_threshold = 100
42
- high_threshold = 200
43
-
44
- image = cv2.Canny(image, low_threshold, high_threshold)
45
- image = image[:, :, None]
46
- image = np.concatenate([image, image, image], axis=2)
47
- image = Image.fromarray(image)
48
-
49
- controlnet = ControlNetModel.from_pretrained(
50
- "fusing/stable-diffusion-v1-5-controlnet-canny",
51
- )
52
-
53
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
54
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
55
- )
56
- pipe.to('cuda')
57
-
58
- image = pipe("bird", image).images[0]
59
-
60
- image.save('images/bird_canny_out.png')
61
- ```
62
-
63
- ![bird](./images/bird.png)
64
-
65
- ![bird_canny](./images/bird_canny.png)
66
-
67
- ![bird_canny_out](./images/bird_canny_out.png)
68
-
69
- ## M-LSD Straight line detection
70
-
71
- Install the additional controlnet models package.
72
-
73
- ```sh
74
- $ pip install git+https://github.com/patrickvonplaten/human_pose.git
75
- ```
76
-
77
- ```py
78
- from PIL import Image
79
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
80
- import torch
81
- from human_pose import MLSDdetector
82
-
83
- mlsd = MLSDdetector.from_pretrained('lllyasviel/ControlNet')
84
-
85
- image = Image.open('images/room.png')
86
-
87
- image = mlsd(image)
88
-
89
- controlnet = ControlNetModel.from_pretrained(
90
- "fusing/stable-diffusion-v1-5-controlnet-mlsd",
91
- )
92
-
93
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
94
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
95
- )
96
- pipe.to('cuda')
97
-
98
- image = pipe("room", image).images[0]
99
-
100
- image.save('images/room_mlsd_out.png')
101
- ```
102
-
103
- ![room](./images/room.png)
104
-
105
- ![room_mlsd](./images/room_mlsd.png)
106
-
107
- ![room_mlsd_out](./images/room_mlsd_out.png)
108
 
109
  ## Pose estimation
110
 
 
 
111
  Install the additional controlnet models package.
112
 
113
  ```sh
114
- $ pip install git+https://github.com/patrickvonplaten/human_pose.git
115
  ```
116
 
117
  ```py
118
  from PIL import Image
119
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
120
  import torch
121
- from human_pose import OpenposeDetector
122
 
123
  openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
124
 
@@ -127,15 +43,23 @@ image = Image.open('images/pose.png')
127
  image = openpose(image)
128
 
129
  controlnet = ControlNetModel.from_pretrained(
130
- "fusing/stable-diffusion-v1-5-controlnet-openpose",
131
  )
132
 
133
  pipe = StableDiffusionControlNetPipeline.from_pretrained(
134
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
135
  )
136
- pipe.to('cuda')
137
 
138
- image = pipe("chef in the kitchen", image).images[0]
 
 
 
 
 
 
 
 
 
139
 
140
  image.save('images/chef_pose_out.png')
141
  ```
@@ -146,236 +70,6 @@ image.save('images/chef_pose_out.png')
146
 
147
  ![chef_pose_out](./images/chef_pose_out.png)
148
 
149
- ## Semantic Segmentation
150
-
151
- Semantic segmentation relies on transformers. Transformers is a
152
- dependency of diffusers for running controlnet, so you should
153
- have it installed already.
154
-
155
- ```py
156
- from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
157
- from PIL import Image
158
- import numpy as np
159
- from controlnet_utils import ade_palette
160
- import torch
161
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
162
-
163
- image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
164
- image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
165
-
166
- image = Image.open("./images/house.png").convert('RGB')
167
-
168
- pixel_values = image_processor(image, return_tensors="pt").pixel_values
169
-
170
- with torch.no_grad():
171
- outputs = image_segmentor(pixel_values)
172
-
173
- seg = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
174
-
175
- color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8) # height, width, 3
176
-
177
- palette = np.array(ade_palette())
178
-
179
- for label, color in enumerate(palette):
180
- color_seg[seg == label, :] = color
181
-
182
- color_seg = color_seg.astype(np.uint8)
183
-
184
- image = Image.fromarray(color_seg)
185
-
186
- controlnet = ControlNetModel.from_pretrained(
187
- "fusing/stable-diffusion-v1-5-controlnet-seg",
188
- )
189
-
190
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
191
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
192
- )
193
- pipe.to('cuda')
194
-
195
- image = pipe("house", image).images[0]
196
-
197
- image.save('./images/house_seg_out.png')
198
- ```
199
-
200
- ![house](images/house.png)
201
-
202
- ![house_seg](images/house_seg.png)
203
-
204
- ![house_seg_out](images/house_seg_out.png)
205
-
206
- ## Depth control
207
-
208
- Depth control relies on transformers. Transformers is a dependency of diffusers for running controlnet, so
209
- you should have it installed already.
210
-
211
- ```py
212
- from transformers import pipeline
213
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
214
- from PIL import Image
215
- import numpy as np
216
-
217
- depth_estimator = pipeline('depth-estimation')
218
-
219
- image = Image.open('./images/stormtrooper.png')
220
- image = depth_estimator(image)['depth']
221
- image = np.array(image)
222
- image = image[:, :, None]
223
- image = np.concatenate([image, image, image], axis=2)
224
- image = Image.fromarray(image)
225
-
226
- controlnet = ControlNetModel.from_pretrained(
227
- "fusing/stable-diffusion-v1-5-controlnet-depth",
228
- )
229
-
230
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
231
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
232
- )
233
- pipe.to('cuda')
234
-
235
- image = pipe("Stormtrooper's lecture", image).images[0]
236
-
237
- image.save('./images/stormtrooper_depth_out.png')
238
- ```
239
-
240
- ![stormtrooper](./images/stormtrooper.png)
241
-
242
- ![stormtrooler_depth](./images/stormtrooper_depth.png)
243
-
244
- ![stormtrooler_depth_out](./images/stormtrooper_depth_out.png)
245
-
246
-
247
- ## Normal map
248
-
249
- ```py
250
- from PIL import Image
251
- from transformers import pipeline
252
- import numpy as np
253
- import cv2
254
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
255
-
256
- image = Image.open("images/toy.png").convert("RGB")
257
-
258
- depth_estimator = pipeline("depth-estimation", model ="Intel/dpt-hybrid-midas" )
259
-
260
- image = depth_estimator(image)['predicted_depth'][0]
261
-
262
- image = image.numpy()
263
-
264
- image_depth = image.copy()
265
- image_depth -= np.min(image_depth)
266
- image_depth /= np.max(image_depth)
267
-
268
- bg_threhold = 0.4
269
-
270
- x = cv2.Sobel(image, cv2.CV_32F, 1, 0, ksize=3)
271
- x[image_depth < bg_threhold] = 0
272
-
273
- y = cv2.Sobel(image, cv2.CV_32F, 0, 1, ksize=3)
274
- y[image_depth < bg_threhold] = 0
275
-
276
- z = np.ones_like(x) * np.pi * 2.0
277
-
278
- image = np.stack([x, y, z], axis=2)
279
- image /= np.sum(image ** 2.0, axis=2, keepdims=True) ** 0.5
280
- image = (image * 127.5 + 127.5).clip(0, 255).astype(np.uint8)
281
- image = Image.fromarray(image)
282
-
283
- controlnet = ControlNetModel.from_pretrained(
284
- "fusing/stable-diffusion-v1-5-controlnet-normal",
285
- )
286
-
287
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
288
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
289
- )
290
- pipe.to('cuda')
291
-
292
- image = pipe("cute toy", image).images[0]
293
-
294
- image.save('images/toy_normal_out.png')
295
- ```
296
-
297
- ![toy](./images/toy.png)
298
-
299
- ![toy_normal](./images/toy_normal.png)
300
-
301
- ![toy_normal_out](./images/toy_normal_out.png)
302
-
303
- ## Scribble
304
-
305
- Install the additional controlnet models package.
306
-
307
- ```sh
308
- $ pip install git+https://github.com/patrickvonplaten/human_pose.git
309
- ```
310
-
311
- ```py
312
- from PIL import Image
313
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
314
- import torch
315
- from human_pose import HEDdetector
316
-
317
- hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
318
-
319
- image = Image.open('images/bag.png')
320
-
321
- image = hed(image, scribble=True)
322
-
323
- controlnet = ControlNetModel.from_pretrained(
324
- "fusing/stable-diffusion-v1-5-controlnet-scribble",
325
- )
326
-
327
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
328
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
329
- )
330
- pipe.to('cuda')
331
-
332
- image = pipe("bag", image).images[0]
333
-
334
- image.save('images/bag_scribble_out.png')
335
- ```
336
-
337
- ![bag](./images/bag.png)
338
-
339
- ![bag_scribble](./images/bag_scribble.png)
340
-
341
- ![bag_scribble_out](./images/bag_scribble_out.png)
342
-
343
- ## HED Boundary
344
-
345
- Install the additional controlnet models package.
346
-
347
- ```sh
348
- $ pip install git+https://github.com/patrickvonplaten/human_pose.git
349
- ```
350
-
351
- ```py
352
- from PIL import Image
353
- from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
354
- import torch
355
- from human_pose import HEDdetector
356
-
357
- hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
358
-
359
- image = Image.open('images/man.png')
360
-
361
- image = hed(image)
362
-
363
- controlnet = ControlNetModel.from_pretrained(
364
- "fusing/stable-diffusion-v1-5-controlnet-hed",
365
- )
366
-
367
- pipe = StableDiffusionControlNetPipeline.from_pretrained(
368
- "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
369
- )
370
- pipe.to('cuda')
371
-
372
- image = pipe("oil painting of handsome old man, masterpiece", image).images[0]
373
-
374
- image.save('images/man_hed_out.png')
375
- ```
376
-
377
- ![man](./images/man.png)
378
-
379
- ![man_hed](./images/man_hed.png)
380
 
381
- ![man_hed_out](./images/man_hed_out.png)
 
18
  The auxiliary conditioning is passed directly to the diffusers pipeline. If you want to process an image to create the auxiliary conditioning, external dependencies are required.
19
 
20
  Some of the additional conditionings can be extracted from images via additional models. We extracted these
21
+ additional models from the original controlnet repo into a separate package that can be found on [github](https://github.com/patrickvonplaten/controlnet_aux.git).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
 
23
  ## Pose estimation
24
 
25
+ ### Diffusers
26
+
27
  Install the additional controlnet models package.
28
 
29
  ```sh
30
+ $ pip install git+https://github.com/patrickvonplaten/controlnet_aux.git
31
  ```
32
 
33
  ```py
34
  from PIL import Image
35
+ from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
36
  import torch
37
+ from controlnet_aux import OpenposeDetector
38
 
39
  openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
40
 
 
43
  image = openpose(image)
44
 
45
  controlnet = ControlNetModel.from_pretrained(
46
+ "fusing/stable-diffusion-v1-5-controlnet-openpose", torch_dtype=torch.float16
47
  )
48
 
49
  pipe = StableDiffusionControlNetPipeline.from_pretrained(
50
+ "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
51
  )
 
52
 
53
+ pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
54
+
55
+ # Remove if you do not have xformers installed
56
+ # see https://huggingface.co/docs/diffusers/v0.13.0/en/optimization/xformers#installing-xformers
57
+ # for installation instructions
58
+ pipe.enable_xformers_memory_efficient_attention()
59
+
60
+ pipe.enable_model_cpu_offload()
61
+
62
+ image = pipe("chef in the kitchen", image, num_inference_steps=20).images[0]
63
 
64
  image.save('images/chef_pose_out.png')
65
  ```
 
70
 
71
  ![chef_pose_out](./images/chef_pose_out.png)
72
 
73
+ ### Training
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
+ The Openpose model was trained on 200k pose-image, caption pairs. The pose estimation images were generated with Openpose. The model was trained for 300 GPU-hours with Nvidia A100 80G using Stable Diffusion 1.5 as a base model.
images/bag.png DELETED
Binary file (462 kB)
 
images/bag_scribble.png DELETED
Binary file (11 kB)
 
images/bag_scribble_out.png DELETED
Binary file (556 kB)
 
images/bird.png DELETED

Git LFS Details

  • SHA256: cad49fc7d3071b2bcd078bc8dde365f8fa62eaa6d43705fd50c212794a3aac35
  • Pointer size: 132 Bytes
  • Size of remote file: 1.07 MB
images/bird_canny.png DELETED
Binary file (29.1 kB)
 
images/bird_canny_out.png DELETED
Binary file (845 kB)
 
images/chef_pose_out.png CHANGED
images/house.png DELETED
Binary file (391 kB)
 
images/house_seg.png DELETED
Binary file (3.68 kB)
 
images/house_seg_out.png DELETED
Binary file (472 kB)
 
images/man.png DELETED
Binary file (773 kB)
 
images/man_hed.png DELETED
Binary file (118 kB)
 
images/man_hed_out.png DELETED
Binary file (737 kB)
 
images/room.png DELETED
Binary file (637 kB)
 
images/room_mlsd.png DELETED
Binary file (9.06 kB)
 
images/room_mlsd_out.png DELETED
Binary file (575 kB)
 
images/stormtrooper.png DELETED
Binary file (218 kB)
 
images/stormtrooper_depth.png DELETED
Binary file (54.1 kB)
 
images/stormtrooper_depth_out.png DELETED
Binary file (343 kB)
 
images/toy.png DELETED
Binary file (312 kB)
 
images/toy_normal.png DELETED
Binary file (90.1 kB)
 
images/toy_normal_out.png DELETED
Binary file (231 kB)