README update

README.md

@@ -18,240 +18,19 @@ Controlnet's auxiliary models are trained with stable diffusion 1.5. Experimenta
 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.
 
 Some of the additional conditionings can be extracted from images via additional models. We extracted these
-additional models from the original controlnet repo into a separate package that can be found on [github](https://github.com/patrickvonplaten/human_pose.git).
-
-## Canny edge detection
-
-Install opencv
-
-```sh
-$ pip install opencv-contrib-python
-```
-
-```python
-import cv2
-from PIL import Image
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-import torch
-import numpy as np
-
-image = Image.open('images/bird.png')
-image = np.array(image)
-
-low_threshold = 100
-high_threshold = 200
-
-image = cv2.Canny(image, low_threshold, high_threshold)
-image = image[:, :, None]
-image = np.concatenate([image, image, image], axis=2)
-image = Image.fromarray(image)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-canny",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("bird", image).images[0]
-
-image.save('images/bird_canny_out.png')
-```
-
-![bird](./images/bird.png)
-
-![bird_canny](./images/bird_canny.png)
-
-![bird_canny_out](./images/bird_canny_out.png)
-
-## M-LSD Straight line detection
-
-Install the additional controlnet models package.
-
-```sh
-$ pip install git+https://github.com/patrickvonplaten/human_pose.git
-```
-
-```py
-from PIL import Image
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-import torch
-from human_pose import MLSDdetector
-
-mlsd = MLSDdetector.from_pretrained('lllyasviel/ControlNet')
-
-image = Image.open('images/room.png')
-
-image = mlsd(image)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-mlsd",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("room", image).images[0]
-
-image.save('images/room_mlsd_out.png')
-```
-
-![room](./images/room.png)
-
-![room_mlsd](./images/room_mlsd.png)
-
-![room_mlsd_out](./images/room_mlsd_out.png)
-
-## Pose estimation
-
-Install the additional controlnet models package.
-
-```sh
-$ pip install git+https://github.com/patrickvonplaten/human_pose.git
-```
-
-```py
-from PIL import Image
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-import torch
-from human_pose import OpenposeDetector
-
-openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
-
-image = Image.open('images/pose.png')
-
-image = openpose(image)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-openpose",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("chef in the kitchen", image).images[0]
-
-image.save('images/chef_pose_out.png')
-```
-
-![pose](./images/pose.png)
-
-![openpose](./images/openpose.png)
-
-![chef_pose_out](./images/chef_pose_out.png)
-
-## Semantic Segmentation
-
-Semantic segmentation relies on transformers. Transformers is a 
-dependency of diffusers for running controlnet, so you should 
-have it installed already.
-
-```py
-from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
-from PIL import Image
-import numpy as np
-from controlnet_utils import ade_palette
-import torch
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-
-image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
-image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
-
-image = Image.open("./images/house.png").convert('RGB')
-
-pixel_values = image_processor(image, return_tensors="pt").pixel_values
-
-with torch.no_grad():
-  outputs = image_segmentor(pixel_values)
-
-seg = image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
-
-color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8) # height, width, 3
-
-palette = np.array(ade_palette())
-
-for label, color in enumerate(palette):
-    color_seg[seg == label, :] = color
-
-color_seg = color_seg.astype(np.uint8)
-
-image = Image.fromarray(color_seg)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-seg",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("house", image).images[0]
-
-image.save('./images/house_seg_out.png')
-```
-
-![house](images/house.png)
-
-![house_seg](images/house_seg.png)
-
-![house_seg_out](images/house_seg_out.png)
-
-## Depth control
-
-Depth control relies on transformers. Transformers is a dependency of diffusers for running controlnet, so
-you should have it installed already.
-
-```py
-from transformers import pipeline
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-from PIL import Image
-import numpy as np
-
-depth_estimator = pipeline('depth-estimation')
-
-image = Image.open('./images/stormtrooper.png')
-image = depth_estimator(image)['depth']
-image = np.array(image)
-image = image[:, :, None]
-image = np.concatenate([image, image, image], axis=2)
-image = Image.fromarray(image)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-depth",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("Stormtrooper's lecture", image).images[0]
-
-image.save('./images/stormtrooper_depth_out.png')
-```
-
-![stormtrooper](./images/stormtrooper.png)
-
-![stormtrooler_depth](./images/stormtrooper_depth.png)
-
-![stormtrooler_depth_out](./images/stormtrooper_depth_out.png)
-
+additional models from the original controlnet repo into a separate package that can be found on [github](https://github.com/patrickvonplaten/controlnet_aux.git).
 
 ## Normal map
 
+### Diffusers
+
 ```py
 from PIL import Image
 from transformers import pipeline
 import numpy as np
 import cv2
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
+import torch
 
 image = Image.open("images/toy.png").convert("RGB")
 
@@ -281,15 +60,23 @@ image = (image * 127.5 + 127.5).clip(0, 255).astype(np.uint8)
 image = Image.fromarray(image)
 
 controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-normal",
+    "fusing/stable-diffusion-v1-5-controlnet-normal", torch_dtype=torch.float16
 )
 
 pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
+    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
 )
-pipe.to('cuda')
 
-image = pipe("cute toy", image).images[0]
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+# Remove if you do not have xformers installed
+# see https://huggingface.co/docs/diffusers/v0.13.0/en/optimization/xformers#installing-xformers
+# for installation instructions
+pipe.enable_xformers_memory_efficient_attention()
+
+pipe.enable_model_cpu_offload()
+
+image = pipe("cute toy", image, num_inference_steps=20).images[0]
 
 image.save('images/toy_normal_out.png')
 ```
@@ -300,82 +87,10 @@ image.save('images/toy_normal_out.png')
 
 ![toy_normal_out](./images/toy_normal_out.png)
 
-## Scribble
-
-Install the additional controlnet models package.
-
-```sh
-$ pip install git+https://github.com/patrickvonplaten/human_pose.git
-```
-
-```py
-from PIL import Image
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-import torch
-from human_pose import HEDdetector
-
-hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
-
-image = Image.open('images/bag.png')
-
-image = hed(image, scribble=True)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-scribble",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("bag", image).images[0]
-
-image.save('images/bag_scribble_out.png')
-```
-
-![bag](./images/bag.png)
-
-![bag_scribble](./images/bag_scribble.png)
-
-![bag_scribble_out](./images/bag_scribble_out.png)
-
-## HED Boundary
-
-Install the additional controlnet models package.
-
-```sh
-$ pip install git+https://github.com/patrickvonplaten/human_pose.git
-```
-
-```py
-from PIL import Image
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-import torch
-from human_pose import HEDdetector
-
-hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
-
-image = Image.open('images/man.png')
-
-image = hed(image)
-
-controlnet = ControlNetModel.from_pretrained(
-    "fusing/stable-diffusion-v1-5-controlnet-hed",
-)
-
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None
-)
-pipe.to('cuda')
-
-image = pipe("oil painting of handsome old man, masterpiece", image).images[0]
-
-image.save('images/man_hed_out.png')
-```
+### Training
 
-![man](./images/man.png)
+The normal model was trained from an initial model and then a further extended model.
 
-![man_hed](./images/man_hed.png)
+The initial normal model was trained on 25,452 normal-image, caption pairs from DIODE. The image captions were generated by BLIP. The model was trained for 100 GPU-hours with Nvidia A100 80G using Stable Diffusion 1.5 as a base model.
 
-![man_hed_out](./images/man_hed_out.png)
+The extended normal model further trained the initial normal model on "coarse" normal maps. The coarse normal maps were generated using Midas to compute a depth map and then performing normal-from-distance. The model was trained for 200 GPU-hours with Nvidia A100 80G using the initial normal model as a base model.

controlnet_utils.py

@@ -1,40 +0,0 @@
-def ade_palette():
-    """ADE20K palette that maps each class to RGB values."""
-    return [[120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50],
-            [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
-            [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
-            [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
-            [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
-            [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
-            [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
-            [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
-            [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
-            [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
-            [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
-            [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
-            [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
-            [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
-            [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255],
-            [11, 200, 200], [255, 82, 0], [0, 255, 245], [0, 61, 255],
-            [0, 255, 112], [0, 255, 133], [255, 0, 0], [255, 163, 0],
-            [255, 102, 0], [194, 255, 0], [0, 143, 255], [51, 255, 0],
-            [0, 82, 255], [0, 255, 41], [0, 255, 173], [10, 0, 255],
-            [173, 255, 0], [0, 255, 153], [255, 92, 0], [255, 0, 255],
-            [255, 0, 245], [255, 0, 102], [255, 173, 0], [255, 0, 20],
-            [255, 184, 184], [0, 31, 255], [0, 255, 61], [0, 71, 255],
-            [255, 0, 204], [0, 255, 194], [0, 255, 82], [0, 10, 255],
-            [0, 112, 255], [51, 0, 255], [0, 194, 255], [0, 122, 255],
-            [0, 255, 163], [255, 153, 0], [0, 255, 10], [255, 112, 0],
-            [143, 255, 0], [82, 0, 255], [163, 255, 0], [255, 235, 0],
-            [8, 184, 170], [133, 0, 255], [0, 255, 92], [184, 0, 255],
-            [255, 0, 31], [0, 184, 255], [0, 214, 255], [255, 0, 112],
-            [92, 255, 0], [0, 224, 255], [112, 224, 255], [70, 184, 160],
-            [163, 0, 255], [153, 0, 255], [71, 255, 0], [255, 0, 163],
-            [255, 204, 0], [255, 0, 143], [0, 255, 235], [133, 255, 0],
-            [255, 0, 235], [245, 0, 255], [255, 0, 122], [255, 245, 0],
-            [10, 190, 212], [214, 255, 0], [0, 204, 255], [20, 0, 255],
-            [255, 255, 0], [0, 153, 255], [0, 41, 255], [0, 255, 204],
-            [41, 0, 255], [41, 255, 0], [173, 0, 255], [0, 245, 255],
-            [71, 0, 255], [122, 0, 255], [0, 255, 184], [0, 92, 255],
-            [184, 255, 0], [0, 133, 255], [255, 214, 0], [25, 194, 194],
-            [102, 255, 0], [92, 0, 255]]