Delete diffusion_webui

diffusion_webui/controlnet/controlnet_canny.py

@@ -1,176 +0,0 @@
-import cv2
-import gradio as gr
-import numpy as np
-import torch
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_canny_model_list = [
-    "lllyasviel/sd-controlnet-canny",
-    "thibaud/controlnet-sd21-canny-diffusers",
-]
-
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_canny(
-    image_path: str,
-    controlnet_model_path: str,
-):
-    image = Image.open(image_path)
-    image = np.array(image)
-
-    image = cv2.Canny(image, 100, 200)
-    image = image[:, :, None]
-    image = np.concatenate([image, image, image], axis=2)
-    image = Image.fromarray(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        controlnet_model_path, torch_dtype=torch.float16
-    )
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_canny(
-    image_path: str,
-    stable_model_path: str,
-    controlnet_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_canny(
-        image_path=image_path, controlnet_model_path=controlnet_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_canny_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_canny_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_canny_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_canny_model_id = gr.Dropdown(
-                    choices=controlnet_canny_model_list,
-                    value=controlnet_canny_model_list[0],
-                    label="Controlnet Model Id",
-                )
-
-                controlnet_canny_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_canny_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_canny_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_canny_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_canny_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_canny,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_canny_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_canny_image_file,
-                controlnet_canny_stable_model_id,
-                controlnet_canny_model_id,
-                controlnet_canny_prompt,
-                controlnet_canny_negative_prompt,
-                controlnet_canny_guidance_scale,
-                controlnet_canny_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="Controlnet Canny Example",
-        )
-
-        controlnet_canny_predict.click(
-            fn=stable_diffusion_controlnet_canny,
-            inputs=[
-                controlnet_canny_image_file,
-                controlnet_canny_stable_model_id,
-                controlnet_canny_model_id,
-                controlnet_canny_prompt,
-                controlnet_canny_negative_prompt,
-                controlnet_canny_guidance_scale,
-                controlnet_canny_num_inference_step,
-            ],
-            outputs=[output_image],
-        )

diffusion_webui/controlnet/controlnet_depth.py

@@ -1,176 +0,0 @@
-import gradio as gr
-import numpy as np
-import torch
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-from transformers import pipeline
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_depth_model_list = [
-    "lllyasviel/sd-controlnet-depth",
-    "thibaud/controlnet-sd21-depth-diffusers",
-]
-
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_depth(image_path: str, depth_model_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(
-        depth_model_path, torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_depth(
-    image_path: str,
-    stable_model_path: str,
-    depth_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_depth(
-        image_path=image_path, depth_model_path=depth_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_depth_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_depth_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_depth_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_depth_model_id = gr.Dropdown(
-                    choices=controlnet_depth_model_list,
-                    value=controlnet_depth_model_list[0],
-                    label="ControlNet Model Id",
-                )
-
-                controlnet_depth_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_depth_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_depth_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_depth_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_depth_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_depth,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_depth_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_depth_image_file,
-                controlnet_depth_stable_model_id,
-                controlnet_depth_model_id,
-                controlnet_depth_prompt,
-                controlnet_depth_negative_prompt,
-                controlnet_depth_guidance_scale,
-                controlnet_depth_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="ControlNet Depth Example",
-        )
-
-        controlnet_depth_predict.click(
-            fn=stable_diffusion_controlnet_depth,
-            inputs=[
-                controlnet_depth_image_file,
-                controlnet_depth_stable_model_id,
-                controlnet_depth_model_id,
-                controlnet_depth_prompt,
-                controlnet_depth_negative_prompt,
-                controlnet_depth_guidance_scale,
-                controlnet_depth_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/controlnet/controlnet_hed.py

@@ -1,170 +0,0 @@
-import gradio as gr
-import torch
-from controlnet_aux import HEDdetector
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_hed_model_list = [
-    "lllyasviel/sd-controlnet-hed",
-    "thibaud/controlnet-sd21-hed-diffusers",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_hed(image_path: str, controlnet_hed_model_path: str):
-    hed = HEDdetector.from_pretrained("lllyasviel/ControlNet")
-
-    image = Image.open(image_path)
-    image = hed(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        controlnet_hed_model_path, torch_dtype=torch.float16
-    )
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_hed(
-    image_path: str,
-    stable_model_path: str,
-    controlnet_hed_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_hed(
-        image_path=image_path,
-        controlnet_hed_model_path=controlnet_hed_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_hed_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_hed_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_hed_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_hed_model_id = gr.Dropdown(
-                    choices=controlnet_hed_model_list,
-                    value=controlnet_hed_model_list[0],
-                    label="ControlNet Model Id",
-                )
-
-                controlnet_hed_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_hed_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_hed_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_hed_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_hed_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_hed,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_hed_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_hed_image_file,
-                controlnet_hed_stable_model_id,
-                controlnet_hed_model_id,
-                controlnet_hed_prompt,
-                controlnet_hed_negative_prompt,
-                controlnet_hed_guidance_scale,
-                controlnet_hed_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="ControlNet HED Example",
-        )
-
-        controlnet_hed_predict.click(
-            fn=stable_diffusion_controlnet_hed,
-            inputs=[
-                controlnet_hed_image_file,
-                controlnet_hed_stable_model_id,
-                controlnet_hed_model_id,
-                controlnet_hed_prompt,
-                controlnet_hed_negative_prompt,
-                controlnet_hed_guidance_scale,
-                controlnet_hed_num_inference_step,
-            ],
-            outputs=[output_image],
-        )

diffusion_webui/controlnet/controlnet_mlsd.py

@@ -1,153 +0,0 @@
-import gradio as gr
-import torch
-from controlnet_aux import MLSDdetector
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_mlsd(image_path: str):
-    mlsd = MLSDdetector.from_pretrained("lllyasviel/ControlNet")
-
-    image = Image.open(image_path)
-    image = mlsd(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        "lllyasviel/sd-controlnet-mlsd",
-        torch_dtype=torch.float16,
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_mlsd(
-    image_path: str,
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_mlsd(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_mlsd_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_mlsd_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_mlsd_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_mlsd_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_mlsd_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_mlsd_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_mlsd_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_mlsd_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_mlsd,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_mlsd_image_file,
-                controlnet_mlsd_model_id,
-                controlnet_mlsd_prompt,
-                controlnet_mlsd_negative_prompt,
-                controlnet_mlsd_guidance_scale,
-                controlnet_mlsd_num_inference_step,
-            ],
-            outputs=[output_image],
-            label="ControlNet-MLSD Example",
-            cache_examples=False,
-        )
-
-        controlnet_mlsd_predict.click(
-            fn=stable_diffusion_controlnet_mlsd,
-            inputs=[
-                controlnet_mlsd_image_file,
-                controlnet_mlsd_model_id,
-                controlnet_mlsd_prompt,
-                controlnet_mlsd_negative_prompt,
-                controlnet_mlsd_guidance_scale,
-                controlnet_mlsd_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/controlnet/controlnet_pose.py

@@ -1,170 +0,0 @@
-import gradio as gr
-import torch
-from controlnet_aux import OpenposeDetector
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_pose_model_list = [
-    "lllyasviel/sd-controlnet-openpose",
-    "thibaud/controlnet-sd21-openpose-diffusers",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_pose(image_path: str, controlnet_pose_model_path: str):
-    openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
-
-    image = Image.open(image_path)
-    image = openpose(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        controlnet_pose_model_path, torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_pose(
-    image_path: str,
-    stable_model_path: str,
-    controlnet_pose_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_pose(
-        image_path=image_path,
-        controlnet_pose_model_path=controlnet_pose_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_pose_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_pose_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_pose_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_pose_model_id = gr.Dropdown(
-                    choices=controlnet_pose_model_list,
-                    value=controlnet_pose_model_list[0],
-                    label="ControlNet Model Id",
-                )
-
-                controlnet_pose_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_pose_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_pose_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_pose_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_pose_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_pose,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_pose_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_pose_image_file,
-                controlnet_pose_stable_model_id,
-                controlnet_pose_model_id,
-                controlnet_pose_prompt,
-                controlnet_pose_negative_prompt,
-                controlnet_pose_guidance_scale,
-                controlnet_pose_num_inference_step,
-            ],
-            outputs=[output_image],
-            label="ControlNet Pose Example",
-            cache_examples=False,
-        )
-        controlnet_pose_predict.click(
-            fn=stable_diffusion_controlnet_pose,
-            inputs=[
-                controlnet_pose_image_file,
-                controlnet_pose_stable_model_id,
-                controlnet_pose_model_id,
-                controlnet_pose_prompt,
-                controlnet_pose_negative_prompt,
-                controlnet_pose_guidance_scale,
-                controlnet_pose_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/controlnet/controlnet_scribble.py

@@ -1,170 +0,0 @@
-import gradio as gr
-import torch
-from controlnet_aux import HEDdetector
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_hed_model_list = [
-    "lllyasviel/sd-controlnet-scribble",
-    "thibaud/controlnet-sd21-scribble-diffusers",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_scribble(image_path: str, controlnet_hed_model_path: str):
-    hed = HEDdetector.from_pretrained("lllyasviel/ControlNet")
-
-    image = Image.open(image_path)
-    image = hed(image, scribble=True)
-
-    controlnet = ControlNetModel.from_pretrained(
-        controlnet_hed_model_path, torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_scribble(
-    image_path: str,
-    stable_model_path: str,
-    controlnet_hed_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_scribble(
-        image_path=image_path,
-        controlnet_hed_model_path=controlnet_hed_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_scribble_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_scribble_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_scribble_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable v1.5 Model Id",
-                )
-
-                controlnet_scribble_model_id = gr.Dropdown(
-                    choices=controlnet_hed_model_list,
-                    value=controlnet_hed_model_list[0],
-                    label="ControlNet Model Id",
-                )
-
-                controlnet_scribble_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_scribble_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_scribble_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_scribble_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_scribble_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_scribble,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_hed_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ],
-            ],
-            inputs=[
-                controlnet_scribble_image_file,
-                controlnet_scribble_stable_model_id,
-                controlnet_scribble_model_id,
-                controlnet_scribble_prompt,
-                controlnet_scribble_negative_prompt,
-                controlnet_scribble_guidance_scale,
-                controlnet_scribble_num_inference_step,
-            ],
-            outputs=[output_image],
-            label="ControlNet Scribble Example",
-            cache_examples=False,
-        )
-        controlnet_scribble_predict.click(
-            fn=stable_diffusion_controlnet_scribble,
-            inputs=[
-                controlnet_scribble_image_file,
-                controlnet_scribble_stable_model_id,
-                controlnet_scribble_model_id,
-                controlnet_scribble_prompt,
-                controlnet_scribble_negative_prompt,
-                controlnet_scribble_guidance_scale,
-                controlnet_scribble_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/controlnet/controlnet_seg.py

@@ -1,329 +0,0 @@
-import gradio as gr
-import numpy as np
-import torch
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-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(
-        "lllyasviel/sd-controlnet-seg", torch_dtype=torch.float16
-    )
-
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_seg(
-    image_path: str,
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_mlsd(image_path=image_path)
-
-    pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        pretrained_model_name_or_path=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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_seg_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_seg_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_seg_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_seg_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_seg_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_seg_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_seg_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_seg_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_seg,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ],
-            ],
-            inputs=[
-                controlnet_seg_image_file,
-                controlnet_seg_model_id,
-                controlnet_seg_prompt,
-                controlnet_seg_negative_prompt,
-                controlnet_seg_guidance_scale,
-                controlnet_seg_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="ControlNet Segmentation Example",
-        )
-
-        controlnet_seg_predict.click(
-            fn=stable_diffusion_controlnet_seg,
-            inputs=[
-                controlnet_seg_image_file,
-                controlnet_seg_model_id,
-                controlnet_seg_prompt,
-                controlnet_seg_negative_prompt,
-                controlnet_seg_guidance_scale,
-                controlnet_seg_num_inference_step,
-            ],
-            outputs=[output_image],
-        )

diffusion_webui/controlnet_inpaint/canny_inpaint.py

@@ -1,176 +0,0 @@
-import cv2
-import gradio as gr
-import numpy as np
-import torch
-from diffusers import (
-    ControlNetModel,
-    StableDiffusionControlNetPipeline,
-    UniPCMultistepScheduler,
-)
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-controlnet_canny_model_list = [
-    "lllyasviel/sd-controlnet-canny",
-    "thibaud/controlnet-sd21-canny-diffusers",
-]
-
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def controlnet_canny(
-    dict_image: str,
-    controlnet_model_path: str,
-):
-    image = dict_image["image"].convert("RGB").resize((512, 512))
-    image = np.array(image)
-
-    image = cv2.Canny(image, 100, 200)
-    image = image[:, :, None]
-    image = np.concatenate([image, image, image], axis=2)
-    image = Image.fromarray(image)
-
-    controlnet = ControlNetModel.from_pretrained(
-        controlnet_model_path, torch_dtype=torch.float16
-    )
-    return controlnet, image
-
-
-def stable_diffusion_controlnet_canny(
-    image_path: str,
-    stable_model_path: str,
-    controlnet_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    controlnet, image = controlnet_canny(
-        image_path=image_path, controlnet_model_path=controlnet_model_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_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_controlnet_canny_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                controlnet_canny_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                controlnet_canny_stable_model_id = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Stable Model Id",
-                )
-
-                controlnet_canny_model_id = gr.Dropdown(
-                    choices=controlnet_canny_model_list,
-                    value=controlnet_canny_model_list[0],
-                    label="Controlnet Model Id",
-                )
-
-                controlnet_canny_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                controlnet_canny_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_canny_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    controlnet_canny_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                controlnet_canny_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_controlnet_canny,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    controlnet_canny_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ]
-            ],
-            inputs=[
-                controlnet_canny_image_file,
-                controlnet_canny_stable_model_id,
-                controlnet_canny_model_id,
-                controlnet_canny_prompt,
-                controlnet_canny_negative_prompt,
-                controlnet_canny_guidance_scale,
-                controlnet_canny_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="Controlnet Canny Example",
-        )
-
-        controlnet_canny_predict.click(
-            fn=stable_diffusion_controlnet_canny,
-            inputs=[
-                controlnet_canny_image_file,
-                controlnet_canny_stable_model_id,
-                controlnet_canny_model_id,
-                controlnet_canny_prompt,
-                controlnet_canny_negative_prompt,
-                controlnet_canny_guidance_scale,
-                controlnet_canny_num_inference_step,
-            ],
-            outputs=[output_image],
-        )

diffusion_webui/controlnet_inpaint/controlnet_inpaint_app.py

@@ -1,159 +0,0 @@
-import gradio as gr
-import numpy as np
-import torch
-from diffusers import UniPCMultistepScheduler
-from PIL import Image
-
-from diffusion_webui.controlnet_inpaint.canny_inpaint import controlnet_canny
-from diffusion_webui.controlnet_inpaint.pipeline_stable_diffusion_controlnet_inpaint import (
-    StableDiffusionControlNetInpaintPipeline,
-)
-
-stable_inpaint_model_list = [
-    "runwayml/stable-diffusion-inpainting",
-    "stabilityai/stable-diffusion-2-inpainting",
-]
-
-controlnet_model_list = [
-    "lllyasviel/sd-controlnet-canny",
-]
-
-prompt_list = [
-    "a red panda sitting on a bench",
-]
-
-negative_prompt_list = [
-    "bad, ugly",
-]
-
-
-def load_img(image_path: str):
-    image = Image.open(image_path)
-    image = np.array(image)
-    image = Image.fromarray(image)
-
-    return image
-
-
-def stable_diffusion_inpiant_controlnet_canny(
-    dict_image: str,
-    stable_model_path: str,
-    controlnet_model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    controlnet_conditioning_scale: str,
-    guidance_scale: int,
-    num_inference_steps: int,
-):
-    normal_image = dict_image["image"].convert("RGB").resize((512, 512))
-    mask_image = dict_image["mask"].convert("RGB").resize((512, 512))
-
-    controlnet, control_image = controlnet_canny(
-        dict_image=dict_image,
-        controlnet_model_path=controlnet_model_path,
-    )
-
-    pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-        pretrained_model_name_or_path=stable_model_path,
-        controlnet=controlnet,
-        torch_dtype=torch.float16,
-    )
-    pipe.to("cuda")
-    pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    generator = torch.manual_seed(0)
-
-    output = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        num_inference_steps=num_inference_steps,
-        generator=generator,
-        image=normal_image,
-        control_image=control_image,
-        controlnet_conditioning_scale=controlnet_conditioning_scale,
-        guidance_scale=guidance_scale,
-        mask_image=mask_image,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_inpiant_controlnet_canny_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                inpaint_image_file = gr.Image(
-                    source="upload",
-                    tool="sketch",
-                    elem_id="image_upload",
-                    type="pil",
-                    label="Upload",
-                )
-
-                inpaint_model_id = gr.Dropdown(
-                    choices=stable_inpaint_model_list,
-                    value=stable_inpaint_model_list[0],
-                    label="Inpaint Model Id",
-                )
-
-                inpaint_controlnet_model_id = gr.Dropdown(
-                    choices=controlnet_model_list,
-                    value=controlnet_model_list[0],
-                    label="ControlNet Model Id",
-                )
-
-                inpaint_prompt = gr.Textbox(
-                    lines=1, value=prompt_list[0], label="Prompt"
-                )
-
-                inpaint_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    controlnet_conditioning_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=1,
-                        step=0.1,
-                        value=0.5,
-                        label="ControlNet Conditioning Scale",
-                    )
-
-                    inpaint_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    inpaint_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                inpaint_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Outputs")
-
-        inpaint_predict.click(
-            fn=stable_diffusion_inpiant_controlnet_canny,
-            inputs=[
-                inpaint_image_file,
-                inpaint_model_id,
-                inpaint_controlnet_model_id,
-                inpaint_prompt,
-                inpaint_negative_prompt,
-                controlnet_conditioning_scale,
-                inpaint_guidance_scale,
-                inpaint_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/controlnet_inpaint/pipeline_stable_diffusion_controlnet_inpaint.py

@@ -1,607 +0,0 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import numpy as np
-import PIL.Image
-import torch
-from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import *
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> # !pip install opencv-python transformers accelerate
-        >>> from diffusers import StableDiffusionControlNetInpaintPipeline, ControlNetModel, UniPCMultistepScheduler
-        >>> from diffusers.utils import load_image
-        >>> import numpy as np
-        >>> import torch
-
-        >>> import cv2
-        >>> from PIL import Image
-        >>> # download an image
-        >>> image = load_image(
-        ...     "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
-        ... )
-        >>> image = np.array(image)
-        >>> mask_image = load_image(
-        ...     "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
-        ... )
-        >>> mask_image = np.array(mask_image)
-        >>> # get canny image
-        >>> canny_image = cv2.Canny(image, 100, 200)
-        >>> canny_image = canny_image[:, :, None]
-        >>> canny_image = np.concatenate([canny_image, canny_image, canny_image], axis=2)
-        >>> canny_image = Image.fromarray(canny_image)
-
-        >>> # load control net and stable diffusion v1-5
-        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
-        >>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
-        ...     "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16
-        ... )
-
-        >>> # speed up diffusion process with faster scheduler and memory optimization
-        >>> pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-        >>> # remove following line if xformers is not installed
-        >>> pipe.enable_xformers_memory_efficient_attention()
-
-        >>> pipe.enable_model_cpu_offload()
-
-        >>> # generate image
-        >>> generator = torch.manual_seed(0)
-        >>> image = pipe(
-        ...     "futuristic-looking doggo",
-        ...     num_inference_steps=20,
-        ...     generator=generator,
-        ...     image=image,
-        ...     control_image=canny_image,
-        ...     mask_image=mask_image
-        ... ).images[0]
-        ```
-"""
-
-
-def prepare_mask_and_masked_image(image, mask):
-    """
-    Prepares a pair (image, mask) to be consumed by the Stable Diffusion pipeline. This means that those inputs will be
-    converted to ``torch.Tensor`` with shapes ``batch x channels x height x width`` where ``channels`` is ``3`` for the
-    ``image`` and ``1`` for the ``mask``.
-    The ``image`` will be converted to ``torch.float32`` and normalized to be in ``[-1, 1]``. The ``mask`` will be
-    binarized (``mask > 0.5``) and cast to ``torch.float32`` too.
-    Args:
-        image (Union[np.array, PIL.Image, torch.Tensor]): The image to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width x 3`` ``np.array`` or a ``channels x height x width``
-            ``torch.Tensor`` or a ``batch x channels x height x width`` ``torch.Tensor``.
-        mask (_type_): The mask to apply to the image, i.e. regions to inpaint.
-            It can be a ``PIL.Image``, or a ``height x width`` ``np.array`` or a ``1 x height x width``
-            ``torch.Tensor`` or a ``batch x 1 x height x width`` ``torch.Tensor``.
-    Raises:
-        ValueError: ``torch.Tensor`` images should be in the ``[-1, 1]`` range. ValueError: ``torch.Tensor`` mask
-        should be in the ``[0, 1]`` range. ValueError: ``mask`` and ``image`` should have the same spatial dimensions.
-        TypeError: ``mask`` is a ``torch.Tensor`` but ``image`` is not
-            (ot the other way around).
-    Returns:
-        tuple[torch.Tensor]: The pair (mask, masked_image) as ``torch.Tensor`` with 4
-            dimensions: ``batch x channels x height x width``.
-    """
-    if isinstance(image, torch.Tensor):
-        if not isinstance(mask, torch.Tensor):
-            raise TypeError(
-                f"`image` is a torch.Tensor but `mask` (type: {type(mask)} is not"
-            )
-
-        # Batch single image
-        if image.ndim == 3:
-            assert (
-                image.shape[0] == 3
-            ), "Image outside a batch should be of shape (3, H, W)"
-            image = image.unsqueeze(0)
-
-        # Batch and add channel dim for single mask
-        if mask.ndim == 2:
-            mask = mask.unsqueeze(0).unsqueeze(0)
-
-        # Batch single mask or add channel dim
-        if mask.ndim == 3:
-            # Single batched mask, no channel dim or single mask not batched but channel dim
-            if mask.shape[0] == 1:
-                mask = mask.unsqueeze(0)
-
-            # Batched masks no channel dim
-            else:
-                mask = mask.unsqueeze(1)
-
-        assert (
-            image.ndim == 4 and mask.ndim == 4
-        ), "Image and Mask must have 4 dimensions"
-        assert (
-            image.shape[-2:] == mask.shape[-2:]
-        ), "Image and Mask must have the same spatial dimensions"
-        assert (
-            image.shape[0] == mask.shape[0]
-        ), "Image and Mask must have the same batch size"
-
-        # Check image is in [-1, 1]
-        if image.min() < -1 or image.max() > 1:
-            raise ValueError("Image should be in [-1, 1] range")
-
-        # Check mask is in [0, 1]
-        if mask.min() < 0 or mask.max() > 1:
-            raise ValueError("Mask should be in [0, 1] range")
-
-        # Binarize mask
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-
-        # Image as float32
-        image = image.to(dtype=torch.float32)
-    elif isinstance(mask, torch.Tensor):
-        raise TypeError(
-            f"`mask` is a torch.Tensor but `image` (type: {type(image)} is not"
-        )
-    else:
-        # preprocess image
-        if isinstance(image, (PIL.Image.Image, np.ndarray)):
-            image = [image]
-
-        if isinstance(image, list) and isinstance(image[0], PIL.Image.Image):
-            image = [np.array(i.convert("RGB"))[None, :] for i in image]
-            image = np.concatenate(image, axis=0)
-        elif isinstance(image, list) and isinstance(image[0], np.ndarray):
-            image = np.concatenate([i[None, :] for i in image], axis=0)
-
-        image = image.transpose(0, 3, 1, 2)
-        image = torch.from_numpy(image).to(dtype=torch.float32) / 127.5 - 1.0
-
-        # preprocess mask
-        if isinstance(mask, (PIL.Image.Image, np.ndarray)):
-            mask = [mask]
-
-        if isinstance(mask, list) and isinstance(mask[0], PIL.Image.Image):
-            mask = np.concatenate(
-                [np.array(m.convert("L"))[None, None, :] for m in mask], axis=0
-            )
-            mask = mask.astype(np.float32) / 255.0
-        elif isinstance(mask, list) and isinstance(mask[0], np.ndarray):
-            mask = np.concatenate([m[None, None, :] for m in mask], axis=0)
-
-        mask[mask < 0.5] = 0
-        mask[mask >= 0.5] = 1
-        mask = torch.from_numpy(mask)
-
-    masked_image = image * (mask < 0.5)
-
-    return mask, masked_image
-
-
-class StableDiffusionControlNetInpaintPipeline(
-    StableDiffusionControlNetPipeline
-):
-    r"""
-    Pipeline for text-guided image inpainting using Stable Diffusion with ControlNet guidance.
-
-    This model inherits from [`StableDiffusionControlNetPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion uses the text portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
-            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        controlnet ([`ControlNetModel`]):
-            Provides additional conditioning to the unet during the denoising process
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-        safety_checker ([`StableDiffusionSafetyChecker`]):
-            Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
-            Model that extracts features from generated images to be used as inputs for the `safety_checker`.
-    """
-
-    def prepare_mask_latents(
-        self,
-        mask,
-        masked_image,
-        batch_size,
-        height,
-        width,
-        dtype,
-        device,
-        generator,
-        do_classifier_free_guidance,
-    ):
-        # resize the mask to latents shape as we concatenate the mask to the latents
-        # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
-        # and half precision
-        mask = torch.nn.functional.interpolate(
-            mask,
-            size=(
-                height // self.vae_scale_factor,
-                width // self.vae_scale_factor,
-            ),
-        )
-        mask = mask.to(device=device, dtype=dtype)
-
-        masked_image = masked_image.to(device=device, dtype=dtype)
-
-        # encode the mask image into latents space so we can concatenate it to the latents
-        if isinstance(generator, list):
-            masked_image_latents = [
-                self.vae.encode(masked_image[i : i + 1]).latent_dist.sample(
-                    generator=generator[i]
-                )
-                for i in range(batch_size)
-            ]
-            masked_image_latents = torch.cat(masked_image_latents, dim=0)
-        else:
-            masked_image_latents = self.vae.encode(
-                masked_image
-            ).latent_dist.sample(generator=generator)
-        masked_image_latents = (
-            self.vae.config.scaling_factor * masked_image_latents
-        )
-
-        # duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
-        if mask.shape[0] < batch_size:
-            if not batch_size % mask.shape[0] == 0:
-                raise ValueError(
-                    "The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
-                    f" a total batch size of {batch_size}, but {mask.shape[0]} masks were passed. Make sure the number"
-                    " of masks that you pass is divisible by the total requested batch size."
-                )
-            mask = mask.repeat(batch_size // mask.shape[0], 1, 1, 1)
-        if masked_image_latents.shape[0] < batch_size:
-            if not batch_size % masked_image_latents.shape[0] == 0:
-                raise ValueError(
-                    "The passed images and the required batch size don't match. Images are supposed to be duplicated"
-                    f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
-                    " Make sure the number of images that you pass is divisible by the total requested batch size."
-                )
-            masked_image_latents = masked_image_latents.repeat(
-                batch_size // masked_image_latents.shape[0], 1, 1, 1
-            )
-
-        mask = torch.cat([mask] * 2) if do_classifier_free_guidance else mask
-        masked_image_latents = (
-            torch.cat([masked_image_latents] * 2)
-            if do_classifier_free_guidance
-            else masked_image_latents
-        )
-
-        # aligning device to prevent device errors when concating it with the latent model input
-        masked_image_latents = masked_image_latents.to(
-            device=device, dtype=dtype
-        )
-        return mask, masked_image_latents
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        control_image: Union[
-            torch.FloatTensor,
-            PIL.Image.Image,
-            List[torch.FloatTensor],
-            List[PIL.Image.Image],
-        ] = None,
-        mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        guidance_scale: float = 7.5,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        num_images_per_prompt: Optional[int] = 1,
-        eta: float = 0.0,
-        generator: Optional[
-            Union[torch.Generator, List[torch.Generator]]
-        ] = None,
-        latents: Optional[torch.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        callback: Optional[
-            Callable[[int, int, torch.FloatTensor], None]
-        ] = None,
-        callback_steps: int = 1,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        controlnet_conditioning_scale: float = 1.0,
-    ):
-        r"""
-        Function invoked when calling the pipeline for generation.
-        Args:
-            prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
-                instead.
-            image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
-                be masked out with `mask_image` and repainted according to `prompt`.
-            control_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]` or `List[PIL.Image.Image]`):
-                The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
-                the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. PIL.Image.Image` can
-                also be accepted as an image. The control image is automatically resized to fit the output image.
-            mask_image (`PIL.Image.Image`):
-                `Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
-                repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
-                to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
-                instead of 3, so the expected shape would be `(B, H, W, 1)`.
-            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The height in pixels of the generated image.
-            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
-                The width in pixels of the generated image.
-            num_inference_steps (`int`, *optional*, defaults to 50):
-                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
-                expense of slower inference.
-            guidance_scale (`float`, *optional*, defaults to 7.5):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            negative_prompt (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation. If not defined, one has to pass
-                `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
-                Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            num_images_per_prompt (`int`, *optional*, defaults to 1):
-                The number of images to generate per prompt.
-            eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
-                [`schedulers.DDIMScheduler`], will be ignored for others.
-            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
-                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
-                to make generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
-                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
-                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
-                tensor will ge generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
-                provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
-                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
-                argument.
-            output_type (`str`, *optional*, defaults to `"pil"`):
-                The output format of the generate image. Choose between
-                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
-                plain tuple.
-            callback (`Callable`, *optional*):
-                A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
-            callback_steps (`int`, *optional*, defaults to 1):
-                The frequency at which the `callback` function will be called. If not specified, the callback will be
-                called at every step.
-            cross_attention_kwargs (`dict`, *optional*):
-                A kwargs dictionary that if specified is passed along to the `AttnProcessor` as defined under
-                `self.processor` in
-                [diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
-            controlnet_conditioning_scale (`float`, *optional*, defaults to 1.0):
-                The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added
-                to the residual in the original unet.
-        Examples:
-        Returns:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
-            When returning a tuple, the first element is a list with the generated images, and the second element is a
-            list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
-            (nsfw) content, according to the `safety_checker`.
-        """
-        # 0. Default height and width to unet
-        height, width = self._default_height_width(height, width, control_image)
-
-        # 1. Check inputs. Raise error if not correct
-        self.check_inputs(
-            prompt,
-            control_image,
-            height,
-            width,
-            callback_steps,
-            negative_prompt,
-            prompt_embeds,
-            negative_prompt_embeds,
-        )
-
-        # 2. Define call parameters
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        device = self._execution_device
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
-        # 3. Encode input prompt
-        prompt_embeds = self._encode_prompt(
-            prompt,
-            device,
-            num_images_per_prompt,
-            do_classifier_free_guidance,
-            negative_prompt,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-        )
-
-        # 4. Prepare image
-        control_image = self.prepare_image(
-            control_image,
-            width,
-            height,
-            batch_size * num_images_per_prompt,
-            num_images_per_prompt,
-            device,
-            self.controlnet.dtype,
-        )
-
-        if do_classifier_free_guidance:
-            control_image = torch.cat([control_image] * 2)
-
-        # 5. Prepare timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
-        timesteps = self.scheduler.timesteps
-
-        # 6. Prepare latent variables
-        num_channels_latents = self.controlnet.in_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-        )
-
-        # EXTRA: prepare mask latents
-        mask, masked_image = prepare_mask_and_masked_image(image, mask_image)
-        mask, masked_image_latents = self.prepare_mask_latents(
-            mask,
-            masked_image,
-            batch_size * num_images_per_prompt,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            do_classifier_free_guidance,
-        )
-
-        # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        # 8. Denoising loop
-        num_warmup_steps = (
-            len(timesteps) - num_inference_steps * self.scheduler.order
-        )
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # expand the latents if we are doing classifier free guidance
-                latent_model_input = (
-                    torch.cat([latents] * 2)
-                    if do_classifier_free_guidance
-                    else latents
-                )
-                latent_model_input = self.scheduler.scale_model_input(
-                    latent_model_input, t
-                )
-
-                down_block_res_samples, mid_block_res_sample = self.controlnet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    controlnet_cond=control_image,
-                    return_dict=False,
-                )
-
-                down_block_res_samples = [
-                    down_block_res_sample * controlnet_conditioning_scale
-                    for down_block_res_sample in down_block_res_samples
-                ]
-                mid_block_res_sample *= controlnet_conditioning_scale
-
-                # predict the noise residual
-                latent_model_input = torch.cat(
-                    [latent_model_input, mask, masked_image_latents], dim=1
-                )
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    cross_attention_kwargs=cross_attention_kwargs,
-                    down_block_additional_residuals=down_block_res_samples,
-                    mid_block_additional_residual=mid_block_res_sample,
-                ).sample
-
-                # perform guidance
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (
-                        noise_pred_text - noise_pred_uncond
-                    )
-
-                # compute the previous noisy sample x_t -> x_t-1
-                latents = self.scheduler.step(
-                    noise_pred, t, latents, **extra_step_kwargs
-                ).prev_sample
-
-                # call the callback, if provided
-                if i == len(timesteps) - 1 or (
-                    (i + 1) > num_warmup_steps
-                    and (i + 1) % self.scheduler.order == 0
-                ):
-                    progress_bar.update()
-                    if callback is not None and i % callback_steps == 0:
-                        callback(i, t, latents)
-
-        # If we do sequential model offloading, let's offload unet and controlnet
-        # manually for max memory savings
-        if (
-            hasattr(self, "final_offload_hook")
-            and self.final_offload_hook is not None
-        ):
-            self.unet.to("cpu")
-            self.controlnet.to("cpu")
-            torch.cuda.empty_cache()
-
-        if output_type == "latent":
-            image = latents
-            has_nsfw_concept = None
-        elif output_type == "pil":
-            # 8. Post-processing
-            image = self.decode_latents(latents)
-
-            # 9. Run safety checker
-            image, has_nsfw_concept = self.run_safety_checker(
-                image, device, prompt_embeds.dtype
-            )
-
-            # 10. Convert to PIL
-            image = self.numpy_to_pil(image)
-        else:
-            # 8. Post-processing
-            image = self.decode_latents(latents)
-
-            # 9. Run safety checker
-            image, has_nsfw_concept = self.run_safety_checker(
-                image, device, prompt_embeds.dtype
-            )
-
-        # Offload last model to CPU
-        if (
-            hasattr(self, "final_offload_hook")
-            and self.final_offload_hook is not None
-        ):
-            self.final_offload_hook.offload()
-
-        if not return_dict:
-            return (image, has_nsfw_concept)
-
-        return StableDiffusionPipelineOutput(
-            images=image, nsfw_content_detected=has_nsfw_concept
-        )

diffusion_webui/helpers.py

@@ -1,48 +0,0 @@
-from diffusion_webui.controlnet.controlnet_canny import (
-    stable_diffusion_controlnet_canny,
-    stable_diffusion_controlnet_canny_app,
-)
-from diffusion_webui.controlnet.controlnet_depth import (
-    stable_diffusion_controlnet_depth,
-    stable_diffusion_controlnet_depth_app,
-)
-from diffusion_webui.controlnet.controlnet_hed import (
-    stable_diffusion_controlnet_hed,
-    stable_diffusion_controlnet_hed_app,
-)
-from diffusion_webui.controlnet.controlnet_mlsd import (
-    stable_diffusion_controlnet_mlsd,
-    stable_diffusion_controlnet_mlsd_app,
-)
-from diffusion_webui.controlnet.controlnet_pose import (
-    stable_diffusion_controlnet_pose,
-    stable_diffusion_controlnet_pose_app,
-)
-from diffusion_webui.controlnet.controlnet_scribble import (
-    stable_diffusion_controlnet_scribble,
-    stable_diffusion_controlnet_scribble_app,
-)
-from diffusion_webui.controlnet.controlnet_seg import (
-    stable_diffusion_controlnet_seg,
-    stable_diffusion_controlnet_seg_app,
-)
-from diffusion_webui.controlnet_inpaint.controlnet_inpaint_app import (
-    stable_diffusion_inpiant_controlnet_canny,
-    stable_diffusion_inpiant_controlnet_canny_app,
-)
-from diffusion_webui.stable_diffusion.img2img_app import (
-    stable_diffusion_img2img,
-    stable_diffusion_img2img_app,
-)
-from diffusion_webui.stable_diffusion.inpaint_app import (
-    stable_diffusion_inpaint,
-    stable_diffusion_inpaint_app,
-)
-from diffusion_webui.stable_diffusion.keras_txt2img import (
-    keras_stable_diffusion,
-    keras_stable_diffusion_app,
-)
-from diffusion_webui.stable_diffusion.text2img_app import (
-    stable_diffusion_text2img,
-    stable_diffusion_text2img_app,
-)

diffusion_webui/stable_diffusion/img2img_app.py

@@ -1,131 +0,0 @@
-import gradio as gr
-import torch
-from diffusers import DDIMScheduler, StableDiffusionImg2ImgPipeline
-from PIL import Image
-
-stable_model_list = [
-    "runwayml/stable-diffusion-v1-5",
-    "stabilityai/stable-diffusion-2-1",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-data_list = [
-    "data/test.png",
-]
-
-
-def stable_diffusion_img2img(
-    image_path: str,
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    image = Image.open(image_path)
-
-    pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-        model_path, safety_checker=None, torch_dtype=torch.float16
-    )
-    pipe.to("cuda")
-    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    output = pipe(
-        prompt=prompt,
-        image=image,
-        negative_prompt=negative_prompt,
-        num_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_img2img_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                image2image2_image_file = gr.Image(
-                    type="filepath", label="Image"
-                )
-
-                image2image_model_path = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Image-Image Model Id",
-                )
-
-                image2image_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                image2image_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    image2image_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    image2image_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                image2image_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            fn=stable_diffusion_img2img,
-            examples=[
-                [
-                    data_list[0],
-                    stable_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                ],
-            ],
-            inputs=[
-                image2image2_image_file,
-                image2image_model_path,
-                image2image_prompt,
-                image2image_negative_prompt,
-                image2image_guidance_scale,
-                image2image_num_inference_step,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            label="Image-Image Generator",
-        )
-
-        image2image_predict.click(
-            fn=stable_diffusion_img2img,
-            inputs=[
-                image2image2_image_file,
-                image2image_model_path,
-                image2image_prompt,
-                image2image_negative_prompt,
-                image2image_guidance_scale,
-                image2image_num_inference_step,
-            ],
-            outputs=[output_image],
-        )

diffusion_webui/stable_diffusion/inpaint_app.py

@@ -1,105 +0,0 @@
-import gradio as gr
-import torch
-from diffusers import DDIMScheduler, DiffusionPipeline
-
-stable_inpiant_model_list = [
-    "stabilityai/stable-diffusion-2-inpainting",
-    "runwayml/stable-diffusion-inpainting",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-
-def stable_diffusion_inpaint(
-    dict: str,
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-):
-
-    image = dict["image"].convert("RGB").resize((512, 512))
-    mask_image = dict["mask"].convert("RGB").resize((512, 512))
-    pipe = DiffusionPipeline.from_pretrained(
-        model_path,
-        revision="fp16",
-        torch_dtype=torch.float16,
-    )
-    pipe.to("cuda")
-
-    output = pipe(
-        prompt=prompt,
-        image=image,
-        mask_image=mask_image,
-        negative_prompt=negative_prompt,
-        num_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return output[0]
-
-
-def stable_diffusion_inpaint_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                inpaint_image_file = gr.Image(
-                    source="upload",
-                    tool="sketch",
-                    elem_id="image_upload",
-                    type="pil",
-                    label="Upload",
-                )
-
-                inpaint_model_id = gr.Dropdown(
-                    choices=stable_inpiant_model_list,
-                    value=stable_inpiant_model_list[0],
-                    label="Inpaint Model Id",
-                )
-
-                inpaint_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                inpaint_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    inpaint_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    inpaint_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                inpaint_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Outputs")
-
-        inpaint_predict.click(
-            fn=stable_diffusion_inpaint,
-            inputs=[
-                inpaint_image_file,
-                inpaint_model_id,
-                inpaint_prompt,
-                inpaint_negative_prompt,
-                inpaint_guidance_scale,
-                inpaint_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/stable_diffusion/keras_txt2img.py

@@ -1,131 +0,0 @@
-import gradio as gr
-from huggingface_hub import from_pretrained_keras
-from keras_cv import models
-from tensorflow import keras
-
-keras_model_list = [
-    "keras-dreambooth/keras_diffusion_lowpoly_world",
-    "keras-dreambooth/keras-diffusion-traditional-furniture",
-]
-
-stable_prompt_list = [
-    "photo of lowpoly_world",
-    "photo of traditional_furniture",
-]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-keras.mixed_precision.set_global_policy("mixed_float16")
-dreambooth_model = models.StableDiffusion(
-    img_width=512,
-    img_height=512,
-    jit_compile=True,
-)
-
-
-def keras_stable_diffusion(
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    num_imgs_to_gen: int,
-    num_steps: int,
-):
-    """
-    This function is used to generate images using our fine-tuned keras dreambooth stable diffusion model.
-    Args:
-        prompt (str): The text input given by the user based on which images will be generated.
-        num_imgs_to_gen (int): The number of images to be generated using given prompt.
-        num_steps (int): The number of denoising steps
-    Returns:
-        generated_img (List): List of images that were generated using the model
-    """
-    loaded_diffusion_model = from_pretrained_keras(model_path)
-    dreambooth_model._diffusion_model = loaded_diffusion_model
-
-    generated_img = dreambooth_model.text_to_image(
-        prompt,
-        negative_prompt=negative_prompt,
-        batch_size=num_imgs_to_gen,
-        num_steps=num_steps,
-    )
-
-    return generated_img
-
-
-def keras_stable_diffusion_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                keras_text2image_model_path = gr.Dropdown(
-                    choices=keras_model_list,
-                    value=keras_model_list[0],
-                    label="Text-Image Model Id",
-                )
-
-                keras_text2image_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                keras_text2image_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                keras_text2image_guidance_scale = gr.Slider(
-                    minimum=0.1,
-                    maximum=15,
-                    step=0.1,
-                    value=7.5,
-                    label="Guidance Scale",
-                )
-
-                keras_text2image_num_inference_step = gr.Slider(
-                    minimum=1,
-                    maximum=100,
-                    step=1,
-                    value=50,
-                    label="Num Inference Step",
-                )
-
-                keras_text2image_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Gallery(label="Outputs").style(grid=(1, 2))
-
-        gr.Examples(
-            fn=keras_stable_diffusion,
-            inputs=[
-                keras_text2image_model_path,
-                keras_text2image_prompt,
-                keras_text2image_negative_prompt,
-                keras_text2image_guidance_scale,
-                keras_text2image_num_inference_step,
-            ],
-            outputs=[output_image],
-            examples=[
-                [
-                    keras_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                    512,
-                    512,
-                ],
-            ],
-            label="Keras Stable Diffusion Example",
-            cache_examples=False,
-        )
-
-        keras_text2image_predict.click(
-            fn=keras_stable_diffusion,
-            inputs=[
-                keras_text2image_model_path,
-                keras_text2image_prompt,
-                keras_text2image_negative_prompt,
-                keras_text2image_guidance_scale,
-                keras_text2image_num_inference_step,
-            ],
-            outputs=output_image,
-        )

diffusion_webui/stable_diffusion/text2img_app.py

@@ -1,139 +0,0 @@
-import gradio as gr
-import torch
-from diffusers import DDIMScheduler, StableDiffusionPipeline
-
-stable_model_list = [
-    "andite/anything-v4.0",
-]
-
-stable_prompt_list = ["a photo of a man.", "a photo of a girl."]
-
-stable_negative_prompt_list = ["bad, ugly", "deformed"]
-
-
-def stable_diffusion_text2img(
-    model_path: str,
-    prompt: str,
-    negative_prompt: str,
-    guidance_scale: int,
-    num_inference_step: int,
-    height: int,
-    width: int,
-):
-
-    pipe = StableDiffusionPipeline.from_pretrained(
-        model_path, safety_checker=None, torch_dtype=torch.float16
-    ).to("cuda")
-
-    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
-    pipe.enable_xformers_memory_efficient_attention()
-
-    images = pipe(
-        prompt,
-        height=height,
-        width=width,
-        negative_prompt=negative_prompt,
-        num_inference_steps=num_inference_step,
-        guidance_scale=guidance_scale,
-    ).images
-
-    return images[0]
-
-
-def stable_diffusion_text2img_app():
-    with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
-                text2image_model_path = gr.Dropdown(
-                    choices=stable_model_list,
-                    value=stable_model_list[0],
-                    label="Text-Image Model Id",
-                )
-
-                text2image_prompt = gr.Textbox(
-                    lines=1, value=stable_prompt_list[0], label="Prompt"
-                )
-
-                text2image_negative_prompt = gr.Textbox(
-                    lines=1,
-                    value=stable_negative_prompt_list[0],
-                    label="Negative Prompt",
-                )
-
-                with gr.Accordion("Advanced Options", open=False):
-                    text2image_guidance_scale = gr.Slider(
-                        minimum=0.1,
-                        maximum=15,
-                        step=0.1,
-                        value=7.5,
-                        label="Guidance Scale",
-                    )
-
-                    text2image_num_inference_step = gr.Slider(
-                        minimum=1,
-                        maximum=100,
-                        step=1,
-                        value=50,
-                        label="Num Inference Step",
-                    )
-
-                    text2image_height = gr.Slider(
-                        minimum=128,
-                        maximum=1280,
-                        step=32,
-                        value=512,
-                        label="Image Height",
-                    )
-
-                    text2image_width = gr.Slider(
-                        minimum=128,
-                        maximum=1280,
-                        step=32,
-                        value=768,
-                        label="Image Width",
-                    )
-
-                text2image_predict = gr.Button(value="Generator")
-
-            with gr.Column():
-                output_image = gr.Image(label="Output")
-
-        gr.Examples(
-            examples=[
-                [
-                    stable_model_list[0],
-                    stable_prompt_list[0],
-                    stable_negative_prompt_list[0],
-                    7.5,
-                    50,
-                    512,
-                    768,
-                ]
-            ],
-            inputs=[
-                text2image_model_path,
-                text2image_prompt,
-                text2image_negative_prompt,
-                text2image_guidance_scale,
-                text2image_num_inference_step,
-                text2image_height,
-                text2image_width,
-            ],
-            outputs=[output_image],
-            cache_examples=False,
-            fn=stable_diffusion_text2img,
-            label="Text2Image Example",
-        )
-        text2image_predict.click(
-            fn=stable_diffusion_text2img,
-            inputs=[
-                text2image_model_path,
-                text2image_prompt,
-                text2image_negative_prompt,
-                text2image_guidance_scale,
-                text2image_num_inference_step,
-                text2image_height,
-                text2image_width,
-            ],
-            outputs=output_image,
-        )