Delete controlnet

controlnet/controlnet_canny.py

@@ -1,66 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-from PIL import Image
-import numpy as np
-import torch
-import cv2
-
-
-def controlnet_canny(
-    image_path:str,
-    low_th:int,
-    high_th:int,
-):
-    image = Image.open(image_path)
-    image = np.array(image)
-
-    image = cv2.Canny(image, low_th, high_th)
-    image = image[:, :, None]
-    image = np.concatenate([image, image, image], axis=2)
-    image = Image.fromarray(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "lllyasviel/sd-controlnet-canny", 
-        torch_dtype=torch.float16
-    )
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_canny(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    low_th:int,
-    high_th:int
-    ):
-
-    controlnet, image = controlnet_canny(
-        image_path=image_path,
-        low_th=low_th,
-        high_th=high_th
-    )
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16,
-    )
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_depth.py

@@ -1,59 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler,
-                       DDIMScheduler)
-
-from transformers import pipeline
-from PIL import Image
-import numpy as np
-import torch
-
-
-def controlnet_depth(image_path:str):
-    depth_estimator = pipeline('depth-estimation')
-
-    image = Image.open(image_path)
-    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", torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-def stable_diffusion_controlnet_depth(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_depth(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_hed.py

@@ -1,54 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-from controlnet_aux import HEDdetector
-from PIL import Image
-import torch
-
-
-def controlnet_hed(image_path:str):
-    hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
-
-    image = Image.open(image_path)
-    image = hed(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "fusing/stable-diffusion-v1-5-controlnet-hed", 
-        torch_dtype=torch.float16
-    )
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_hed(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_hed(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_mlsd.py

@@ -1,54 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-from controlnet_aux import MLSDdetector
-from PIL import Image
-import torch
-
-
-def controlnet_mlsd(image_path:str):
-    mlsd = MLSDdetector.from_pretrained('lllyasviel/ControlNet')
-
-    image = Image.open(image_path)
-    image = mlsd(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "fusing/stable-diffusion-v1-5-controlnet-mlsd", 
-        torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-def stable_diffusion_controlnet_mlsd(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_mlsd(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_pose.py

@@ -1,55 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-from controlnet_aux import OpenposeDetector
-
-from PIL import Image
-import torch
-
-
-def controlnet_pose(image_path:str):
-    openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')
-
-    image = Image.open(image_path)
-    image = openpose(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "fusing/stable-diffusion-v1-5-controlnet-openpose", 
-        torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-def stable_diffusion_controlnet_pose(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_pose(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_scribble.py

@@ -1,54 +0,0 @@
-from diffusers import ( StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-from controlnet_aux import HEDdetector
-
-from PIL import Image
-import torch
-
-
-def controlnet_scribble(image_path:str):
-    hed = HEDdetector.from_pretrained('lllyasviel/ControlNet')
-
-    image = Image.open(image_path)
-    image = hed(image, scribble=True)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "fusing/stable-diffusion-v1-5-controlnet-scribble", torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-def stable_diffusion_controlnet_scribble(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_scribble(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output

controlnet/controlnet_seg.py

@@ -1,113 +0,0 @@
-from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
-import torch
-from diffusers import (StableDiffusionControlNetPipeline, 
-                       ControlNetModel, UniPCMultistepScheduler)
-
-
-from PIL import Image
-import numpy as np
-import torch
-
-
-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]]
-
-
-def controlnet_mlsd(image_path:str):
-    image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
-    image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
-
-    image = Image.open(image_path).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)
-    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", torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_seg(
-    stable_model_path:str,
-    image_path:str,
-    prompt:str,
-    negative_prompt:str,
-    num_samples:int,
-    guidance_scale:int,
-    num_inference_step:int,
-    ):
-
-    controlnet, image = controlnet_mlsd(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path, 
-        controlnet=controlnet, 
-        safety_checker=None, 
-        torch_dtype=torch.float16
-    )
-
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt = prompt,
-        image = image,
-        negative_prompt = negative_prompt,
-        num_images_per_prompt = num_samples,
-        num_inference_steps = num_inference_step,
-        guidance_scale = guidance_scale,
-    ).images
-
-    return output