Upload 15 files

app.py

@@ -1,27 +1,8 @@
 import gradio as gr
 
 from diffusion_webui import (
-    CodeformerUpscalerGenerator,
-    StableDiffusionControlInpaintNetDepthGenerator,
-    StableDiffusionControlNetCannyGenerator,
-    StableDiffusionControlNetDepthGenerator,
-    StableDiffusionControlNetHEDGenerator,
-    StableDiffusionControlNetInpaintCannyGenerator,
-    StableDiffusionControlNetInpaintHedGenerator,
-    StableDiffusionControlNetInpaintMlsdGenerator,
-    StableDiffusionControlNetInpaintPoseGenerator,
-    StableDiffusionControlNetInpaintScribbleGenerator,
-    StableDiffusionControlNetInpaintSegGenerator,
-    StableDiffusionControlNetLineArtAnimeGenerator,
-    StableDiffusionControlNetLineArtGenerator,
-    StableDiffusionControlNetMLSDGenerator,
-    StableDiffusionControlNetNormalGenerator,
-    StableDiffusionControlNetPix2PixGenerator,
-    StableDiffusionControlNetPoseGenerator,
-    StableDiffusionControlNetScribbleGenerator,
-    StableDiffusionControlNetSegGenerator,
-    StableDiffusionControlNetShuffleGenerator,
-    StableDiffusionControlNetSoftEdgeGenerator,
+    StableDiffusionControlNetGenerator,
+    StableDiffusionControlNetInpaintGenerator,
     StableDiffusionImage2ImageGenerator,
     StableDiffusionInpaintGenerator,
     StableDiffusionText2ImageGenerator,
@@ -33,56 +14,16 @@ def diffusion_app():
     with app:
         with gr.Row():
             with gr.Column():
-                with gr.Tab("Text2Img"):
+                with gr.Tab(label="Text2Image"):
                     StableDiffusionText2ImageGenerator.app()
-                with gr.Tab("Img2Img"):
+                with gr.Tab(label="Image2Image"):
                     StableDiffusionImage2ImageGenerator.app()
-                with gr.Tab("Inpaint"):
+                with gr.Tab(label="Inpaint"):
                     StableDiffusionInpaintGenerator.app()
-                with gr.Tab("ControlNet"):
-                    with gr.Tab("Canny"):
-                        StableDiffusionControlNetCannyGenerator.app()
-                    with gr.Tab("Depth"):
-                        StableDiffusionControlNetDepthGenerator.app()
-                    with gr.Tab("HED"):
-                        StableDiffusionControlNetHEDGenerator.app()
-                    with gr.Tab("MLSD"):
-                        StableDiffusionControlNetMLSDGenerator.app()
-                    with gr.Tab("Pose"):
-                        StableDiffusionControlNetPoseGenerator.app()
-                    with gr.Tab("Scribble"):
-                        StableDiffusionControlNetScribbleGenerator.app()
-                    with gr.Tab("Normal"):
-                        StableDiffusionControlNetNormalGenerator.app()
-                    with gr.Tab("Seg"):
-                        StableDiffusionControlNetSegGenerator.app()
-                    with gr.Tab("Shuffle"):
-                        StableDiffusionControlNetShuffleGenerator.app()
-                    with gr.Tab("Pix2Pix"):
-                        StableDiffusionControlNetPix2PixGenerator.app()
-                    with gr.Tab("LineArt"):
-                        StableDiffusionControlNetLineArtGenerator.app()
-                    with gr.Tab("LineArtAnime"):
-                        StableDiffusionControlNetLineArtAnimeGenerator.app()
-                    with gr.Tab("SoftEdge"):
-                        StableDiffusionControlNetSoftEdgeGenerator.app()
-                with gr.Tab("ControlNet Inpaint"):
-                    with gr.Tab("Canny"):
-                        StableDiffusionControlNetInpaintCannyGenerator.app()
-                    with gr.Tab("Depth"):
-                        StableDiffusionControlInpaintNetDepthGenerator.app()
-                    with gr.Tab("HED"):
-                        StableDiffusionControlNetInpaintHedGenerator.app()
-                    with gr.Tab("MLSD"):
-                        StableDiffusionControlNetInpaintMlsdGenerator.app()
-                    with gr.Tab("Pose"):
-                        StableDiffusionControlNetInpaintPoseGenerator.app()
-                    with gr.Tab("Scribble"):
-                        StableDiffusionControlNetInpaintScribbleGenerator.app()
-                    with gr.Tab("Seg"):
-                        StableDiffusionControlNetInpaintSegGenerator.app()
-                with gr.Tab("Upscaler"):
-                    CodeformerUpscalerGenerator.app()
+                with gr.Tab(label="Controlnet"):
+                    StableDiffusionControlNetGenerator.app()
+                with gr.Tab(label="Controlnet Inpaint"):
+                    StableDiffusionControlNetInpaintGenerator.app()
 
     app.queue(concurrency_count=1)
     app.launch(debug=True, enable_queue=True)

diffusion_webui/__init__.py

@@ -0,0 +1,17 @@
+from diffusion_webui.diffusion_models.controlnet_inpaint_pipeline import (
+    StableDiffusionControlNetInpaintGenerator,
+)
+from diffusion_webui.diffusion_models.controlnet_pipeline import (
+    StableDiffusionControlNetGenerator,
+)
+from diffusion_webui.diffusion_models.img2img_app import (
+    StableDiffusionImage2ImageGenerator,
+)
+from diffusion_webui.diffusion_models.inpaint_app import (
+    StableDiffusionInpaintGenerator,
+)
+from diffusion_webui.diffusion_models.text2img_app import (
+    StableDiffusionText2ImageGenerator,
+)
+
+__version__ = "2.5.0"

diffusion_webui/diffusion_models/base_controlnet_pipeline.py

@@ -0,0 +1,31 @@
+class ControlnetPipeline:
+    def __init__(self):
+        self.pipe = None
+
+    def load_model(self, stable_model_path: str, controlnet_model_path: str):
+        raise NotImplementedError()
+
+    def load_image(self, image_path: str):
+        raise NotImplementedError()
+
+    def controlnet_preprocces(self, read_image: str):
+        raise NotImplementedError()
+
+    def generate_image(
+        self,
+        image_path: str,
+        stable_model_path: str,
+        controlnet_model_path: str,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        guidance_scale: int,
+        num_inference_step: int,
+        controlnet_conditioning_scale: int,
+        scheduler: str,
+        seed_generator: int,
+    ):
+        raise NotImplementedError()
+
+    def web_interface():
+        raise NotImplementedError()

diffusion_webui/diffusion_models/controlnet_inpaint_pipeline.py

@@ -0,0 +1,256 @@
+import gradio as gr
+import numpy as np
+import torch
+from diffusers import ControlNetModel, StableDiffusionControlNetInpaintPipeline
+from PIL import Image
+
+from diffusion_webui.diffusion_models.base_controlnet_pipeline import (
+    ControlnetPipeline,
+)
+from diffusion_webui.utils.model_list import (
+    controlnet_model_list,
+    stable_model_list,
+)
+from diffusion_webui.utils.preprocces_utils import PREPROCCES_DICT
+from diffusion_webui.utils.scheduler_list import (
+    SCHEDULER_MAPPING,
+    get_scheduler,
+)
+
+
+class StableDiffusionControlNetInpaintGenerator(ControlnetPipeline):
+    def __init__(self):
+        super().__init__()
+
+    def load_model(self, stable_model_path, controlnet_model_path, scheduler):
+        if self.pipe is None:
+            controlnet = ControlNetModel.from_pretrained(
+                controlnet_model_path, torch_dtype=torch.float16
+            )
+            self.pipe = (
+                StableDiffusionControlNetInpaintPipeline.from_pretrained(
+                    pretrained_model_name_or_path=stable_model_path,
+                    controlnet=controlnet,
+                    safety_checker=None,
+                    torch_dtype=torch.float16,
+                )
+            )
+
+        self.pipe = get_scheduler(pipe=self.pipe, scheduler=scheduler)
+        self.pipe.to("cuda")
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+        return self.pipe
+
+    def load_image(self, image):
+        image = np.array(image)
+        image = Image.fromarray(image)
+        return image
+
+    def controlnet_preprocces(
+        self,
+        read_image: str,
+        preprocces_type: str,
+    ):
+        processed_image = PREPROCCES_DICT[preprocces_type](read_image)
+        return processed_image
+
+    def generate_image(
+        self,
+        image_path: str,
+        stable_model_path: str,
+        controlnet_model_path: str,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        height: int,
+        width: int,
+        strength: int,
+        guess_mode: bool,
+        guidance_scale: int,
+        num_inference_step: int,
+        controlnet_conditioning_scale: int,
+        scheduler: str,
+        seed_generator: int,
+        preprocces_type: str,
+    ):
+        normal_image = image_path["image"].convert("RGB").resize((512, 512))
+        mask_image = image_path["mask"].convert("RGB").resize((512, 512))
+
+        normal_image = self.load_image(image=normal_image)
+        mask_image = self.load_image(image=mask_image)
+
+        control_image = self.controlnet_preprocces(
+            read_image=normal_image, preprocces_type=preprocces_type
+        )
+        pipe = self.load_model(
+            stable_model_path=stable_model_path,
+            controlnet_model_path=controlnet_model_path,
+            scheduler=scheduler,
+        )
+
+        if seed_generator == 0:
+            random_seed = torch.randint(0, 1000000, (1,))
+            generator = torch.manual_seed(random_seed)
+        else:
+            generator = torch.manual_seed(seed_generator)
+
+        output = pipe(
+            prompt=prompt,
+            image=normal_image,
+            height=height,
+            width=width,
+            mask_image=mask_image,
+            strength=strength,
+            guess_mode=guess_mode,
+            control_image=control_image,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_images_per_prompt,
+            num_inference_steps=num_inference_step,
+            guidance_scale=guidance_scale,
+            controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+            generator=generator,
+        ).images
+
+        return output
+
+    def app():
+        with gr.Blocks():
+            with gr.Row():
+                with gr.Column():
+                    controlnet_inpaint_image_path = gr.Image(
+                        source="upload",
+                        tool="sketch",
+                        elem_id="image_upload",
+                        type="pil",
+                        label="Upload",
+                    ).style(height=260)
+
+                    controlnet_inpaint_prompt = gr.Textbox(
+                        lines=1, placeholder="Prompt", show_label=False
+                    )
+                    controlnet_inpaint_negative_prompt = gr.Textbox(
+                        lines=1, placeholder="Negative Prompt", show_label=False
+                    )
+
+                    with gr.Row():
+                        with gr.Column():
+                            controlnet_inpaint_stable_model_path = gr.Dropdown(
+                                choices=stable_model_list,
+                                value=stable_model_list[0],
+                                label="Stable Model Path",
+                            )
+                            controlnet_inpaint_preprocces_type = gr.Dropdown(
+                                choices=list(PREPROCCES_DICT.keys()),
+                                value=list(PREPROCCES_DICT.keys())[0],
+                                label="Preprocess Type",
+                            )
+                            controlnet_inpaint_conditioning_scale = gr.Slider(
+                                minimum=0.0,
+                                maximum=1.0,
+                                step=0.1,
+                                value=1.0,
+                                label="ControlNet Conditioning Scale",
+                            )
+                            controlnet_inpaint_guidance_scale = gr.Slider(
+                                minimum=0.1,
+                                maximum=15,
+                                step=0.1,
+                                value=7.5,
+                                label="Guidance Scale",
+                            )
+                            controlnet_inpaint_height = gr.Slider(
+                                minimum=128,
+                                maximum=1280,
+                                step=32,
+                                value=512,
+                                label="Height",
+                            )
+                            controlnet_inpaint_width = gr.Slider(
+                                minimum=128,
+                                maximum=1280,
+                                step=32,
+                                value=512,
+                                label="Width",
+                            )
+                            controlnet_inpaint_guess_mode = gr.Checkbox(
+                                label="Guess Mode"
+                            )
+
+                        with gr.Column():
+                            controlnet_inpaint_model_path = gr.Dropdown(
+                                choices=controlnet_model_list,
+                                value=controlnet_model_list[0],
+                                label="ControlNet Model Path",
+                            )
+                            controlnet_inpaint_scheduler = gr.Dropdown(
+                                choices=list(SCHEDULER_MAPPING.keys()),
+                                value=list(SCHEDULER_MAPPING.keys())[0],
+                                label="Scheduler",
+                            )
+                            controlnet_inpaint_strength = gr.Slider(
+                                minimum=0.1,
+                                maximum=15,
+                                step=0.1,
+                                value=7.5,
+                                label="Strength",
+                            )
+                            controlnet_inpaint_num_inference_step = gr.Slider(
+                                minimum=1,
+                                maximum=150,
+                                step=1,
+                                value=30,
+                                label="Num Inference Step",
+                            )
+                            controlnet_inpaint_num_images_per_prompt = (
+                                gr.Slider(
+                                    minimum=1,
+                                    maximum=4,
+                                    step=1,
+                                    value=1,
+                                    label="Number Of Images",
+                                )
+                            )
+                            controlnet_inpaint_seed_generator = gr.Slider(
+                                minimum=0,
+                                maximum=1000000,
+                                step=1,
+                                value=0,
+                                label="Seed(0 for random)",
+                            )
+
+                    # Button to generate the image
+                    controlnet_inpaint_predict_button = gr.Button(
+                        value="Generate Image"
+                    )
+
+                with gr.Column():
+                    # Gallery to display the generated images
+                    controlnet_inpaint_output_image = gr.Gallery(
+                        label="Generated images",
+                        show_label=False,
+                        elem_id="gallery",
+                    ).style(grid=(1, 2))
+
+        controlnet_inpaint_predict_button.click(
+            fn=StableDiffusionControlNetInpaintGenerator().generate_image,
+            inputs=[
+                controlnet_inpaint_image_path,
+                controlnet_inpaint_stable_model_path,
+                controlnet_inpaint_model_path,
+                controlnet_inpaint_prompt,
+                controlnet_inpaint_negative_prompt,
+                controlnet_inpaint_num_images_per_prompt,
+                controlnet_inpaint_height,
+                controlnet_inpaint_width,
+                controlnet_inpaint_strength,
+                controlnet_inpaint_guess_mode,
+                controlnet_inpaint_guidance_scale,
+                controlnet_inpaint_num_inference_step,
+                controlnet_inpaint_conditioning_scale,
+                controlnet_inpaint_scheduler,
+                controlnet_inpaint_seed_generator,
+                controlnet_inpaint_preprocces_type,
+            ],
+            outputs=[controlnet_inpaint_output_image],
+        )

diffusion_webui/diffusion_models/controlnet_pipeline.py

@@ -0,0 +1,225 @@
+import gradio as gr
+import torch
+from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
+from PIL import Image
+
+from diffusion_webui.diffusion_models.base_controlnet_pipeline import (
+    ControlnetPipeline,
+)
+from diffusion_webui.utils.model_list import (
+    controlnet_model_list,
+    stable_model_list,
+)
+from diffusion_webui.utils.preprocces_utils import PREPROCCES_DICT
+from diffusion_webui.utils.scheduler_list import (
+    SCHEDULER_MAPPING,
+    get_scheduler,
+)
+
+
+class StableDiffusionControlNetGenerator(ControlnetPipeline):
+    def __init__(self):
+        self.pipe = None
+
+    def load_model(self, stable_model_path, controlnet_model_path, scheduler):
+        if self.pipe is None:
+            controlnet = ControlNetModel.from_pretrained(
+                controlnet_model_path, torch_dtype=torch.float16
+            )
+            self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
+                pretrained_model_name_or_path=stable_model_path,
+                controlnet=controlnet,
+                safety_checker=None,
+                torch_dtype=torch.float16,
+            )
+
+        self.pipe = get_scheduler(pipe=self.pipe, scheduler=scheduler)
+        self.pipe.to("cuda")
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+        return self.pipe
+
+    def controlnet_preprocces(
+        self,
+        read_image: str,
+        preprocces_type: str,
+    ):
+        processed_image = PREPROCCES_DICT[preprocces_type](read_image)
+        return processed_image
+
+    def generate_image(
+        self,
+        image_path: str,
+        stable_model_path: str,
+        controlnet_model_path: str,
+        height: int,
+        width: int,
+        guess_mode: bool,
+        controlnet_conditioning_scale: int,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        guidance_scale: int,
+        num_inference_step: int,
+        scheduler: str,
+        seed_generator: int,
+        preprocces_type: str,
+    ):
+        pipe = self.load_model(
+            stable_model_path=stable_model_path,
+            controlnet_model_path=controlnet_model_path,
+            scheduler=scheduler,
+        )
+
+        read_image = Image.open(image_path)
+        controlnet_image = self.controlnet_preprocces(
+            read_image=read_image, preprocces_type=preprocces_type
+        )
+
+        if seed_generator == 0:
+            random_seed = torch.randint(0, 1000000, (1,))
+            generator = torch.manual_seed(random_seed)
+        else:
+            generator = torch.manual_seed(seed_generator)
+
+        output = pipe(
+            prompt=prompt,
+            height=height,
+            width=width,
+            controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+            guess_mode=guess_mode,
+            image=controlnet_image,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_images_per_prompt,
+            num_inference_steps=num_inference_step,
+            guidance_scale=guidance_scale,
+            generator=generator,
+        ).images
+
+        return output
+
+    def app():
+        with gr.Blocks():
+            with gr.Row():
+                with gr.Column():
+                    controlnet_image_path = gr.Image(
+                        type="filepath", label="Image"
+                    ).style(height=260)
+                    controlnet_prompt = gr.Textbox(
+                        lines=1, placeholder="Prompt", show_label=False
+                    )
+                    controlnet_negative_prompt = gr.Textbox(
+                        lines=1, placeholder="Negative Prompt", show_label=False
+                    )
+
+                    with gr.Row():
+                        with gr.Column():
+                            controlnet_stable_model_path = gr.Dropdown(
+                                choices=stable_model_list,
+                                value=stable_model_list[0],
+                                label="Stable Model Path",
+                            )
+                            controlnet_preprocces_type = gr.Dropdown(
+                                choices=list(PREPROCCES_DICT.keys()),
+                                value=list(PREPROCCES_DICT.keys())[0],
+                                label="Preprocess Type",
+                            )
+                            controlnet_conditioning_scale = gr.Slider(
+                                minimum=0.0,
+                                maximum=1.0,
+                                step=0.1,
+                                value=1.0,
+                                label="ControlNet Conditioning Scale",
+                            )
+                            controlnet_guidance_scale = gr.Slider(
+                                minimum=0.1,
+                                maximum=15,
+                                step=0.1,
+                                value=7.5,
+                                label="Guidance Scale",
+                            )
+                            controlnet_height = gr.Slider(
+                                minimum=128,
+                                maximum=1280,
+                                step=32,
+                                value=512,
+                                label="Height",
+                            )
+                            controlnet_width = gr.Slider(
+                                minimum=128,
+                                maximum=1280,
+                                step=32,
+                                value=512,
+                                label="Width",
+                            )
+
+                        with gr.Row():
+                            with gr.Column():
+                                controlnet_model_path = gr.Dropdown(
+                                    choices=controlnet_model_list,
+                                    value=controlnet_model_list[0],
+                                    label="ControlNet Model Path",
+                                )
+                                controlnet_scheduler = gr.Dropdown(
+                                    choices=list(SCHEDULER_MAPPING.keys()),
+                                    value=list(SCHEDULER_MAPPING.keys())[0],
+                                    label="Scheduler",
+                                )
+                                controlnet_num_inference_step = gr.Slider(
+                                    minimum=1,
+                                    maximum=150,
+                                    step=1,
+                                    value=30,
+                                    label="Num Inference Step",
+                                )
+
+                                controlnet_num_images_per_prompt = gr.Slider(
+                                    minimum=1,
+                                    maximum=4,
+                                    step=1,
+                                    value=1,
+                                    label="Number Of Images",
+                                )
+                                controlnet_seed_generator = gr.Slider(
+                                    minimum=0,
+                                    maximum=1000000,
+                                    step=1,
+                                    value=0,
+                                    label="Seed(0 for random)",
+                                )
+                                controlnet_guess_mode = gr.Checkbox(
+                                    label="Guess Mode"
+                                )
+
+                    # Button to generate the image
+                    predict_button = gr.Button(value="Generate Image")
+
+                with gr.Column():
+                    # Gallery to display the generated images
+                    output_image = gr.Gallery(
+                        label="Generated images",
+                        show_label=False,
+                        elem_id="gallery",
+                    ).style(grid=(1, 2))
+
+        predict_button.click(
+            fn=StableDiffusionControlNetGenerator().generate_image,
+            inputs=[
+                controlnet_image_path,
+                controlnet_stable_model_path,
+                controlnet_model_path,
+                controlnet_height,
+                controlnet_width,
+                controlnet_guess_mode,
+                controlnet_conditioning_scale,
+                controlnet_prompt,
+                controlnet_negative_prompt,
+                controlnet_num_images_per_prompt,
+                controlnet_guidance_scale,
+                controlnet_num_inference_step,
+                controlnet_scheduler,
+                controlnet_seed_generator,
+                controlnet_preprocces_type,
+            ],
+            outputs=[output_image],
+        )

diffusion_webui/diffusion_models/img2img_app.py

@@ -0,0 +1,153 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionImg2ImgPipeline
+from PIL import Image
+
+from diffusion_webui.utils.model_list import stable_model_list
+from diffusion_webui.utils.scheduler_list import (
+    SCHEDULER_MAPPING,
+    get_scheduler,
+)
+
+
+class StableDiffusionImage2ImageGenerator:
+    def __init__(self):
+        self.pipe = None
+
+    def load_model(self, model_path, scheduler):
+        if self.pipe is None:
+            self.pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
+                model_path, safety_checker=None, torch_dtype=torch.float16
+            )
+
+        self.pipe = get_scheduler(pipe=self.pipe, scheduler=scheduler)
+        self.pipe.to("cuda")
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+        return self.pipe
+
+    def generate_image(
+        self,
+        image_path: str,
+        model_path: str,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        scheduler: str,
+        guidance_scale: int,
+        num_inference_step: int,
+        seed_generator=0,
+    ):
+        pipe = self.load_model(
+            model_path=model_path,
+            scheduler=scheduler,
+        )
+
+        if seed_generator == 0:
+            random_seed = torch.randint(0, 1000000, (1,))
+            generator = torch.manual_seed(random_seed)
+        else:
+            generator = torch.manual_seed(seed_generator)
+
+        image = Image.open(image_path)
+        images = pipe(
+            prompt,
+            image=image,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_images_per_prompt,
+            num_inference_steps=num_inference_step,
+            guidance_scale=guidance_scale,
+            generator=generator,
+        ).images
+
+        return images
+
+    def app():
+        with gr.Blocks():
+            with gr.Row():
+                with gr.Column():
+                    image2image_image_file = gr.Image(
+                        type="filepath", label="Image"
+                    ).style(height=260)
+
+                    image2image_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Prompt",
+                        show_label=False,
+                    )
+
+                    image2image_negative_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Negative Prompt",
+                        show_label=False,
+                    )
+
+                    with gr.Row():
+                        with gr.Column():
+                            image2image_model_path = gr.Dropdown(
+                                choices=stable_model_list,
+                                value=stable_model_list[0],
+                                label="Stable Model Id",
+                            )
+
+                            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",
+                            )
+                        with gr.Row():
+                            with gr.Column():
+                                image2image_scheduler = gr.Dropdown(
+                                    choices=list(SCHEDULER_MAPPING.keys()),
+                                    value=list(SCHEDULER_MAPPING.keys())[0],
+                                    label="Scheduler",
+                            )
+                                image2image_num_images_per_prompt = gr.Slider(
+                                    minimum=1,
+                                    maximum=30,
+                                    step=1,
+                                    value=1,
+                                    label="Number Of Images",
+                                )
+
+                                image2image_seed_generator = gr.Slider(
+                                    minimum=0,
+                                    maximum=1000000,
+                                    step=1,
+                                    value=0,
+                                    label="Seed(0 for random)",
+                                )
+
+                    image2image_predict_button = gr.Button(value="Generator")
+
+                with gr.Column():
+                    output_image = gr.Gallery(
+                        label="Generated images",
+                        show_label=False,
+                        elem_id="gallery",
+                    ).style(grid=(1, 2))
+
+        image2image_predict_button.click(
+            fn=StableDiffusionImage2ImageGenerator().generate_image,
+            inputs=[
+                image2image_image_file,
+                image2image_model_path,
+                image2image_prompt,
+                image2image_negative_prompt,
+                image2image_num_images_per_prompt,
+                image2image_scheduler,
+                image2image_guidance_scale,
+                image2image_num_inference_step,
+                image2image_seed_generator,
+            ],
+            outputs=[output_image],
+        )

diffusion_webui/diffusion_models/inpaint_app.py

@@ -0,0 +1,148 @@
+import gradio as gr
+import torch
+from diffusers import DiffusionPipeline
+
+from diffusion_webui.utils.model_list import stable_inpiant_model_list
+
+
+class StableDiffusionInpaintGenerator:
+    def __init__(self):
+        self.pipe = None
+
+    def load_model(self, model_path):
+        if self.pipe is None:
+            self.pipe = DiffusionPipeline.from_pretrained(
+                model_path, revision="fp16", torch_dtype=torch.float16
+            )
+
+        self.pipe.to("cuda")
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+        return self.pipe
+
+    def generate_image(
+        self,
+        pil_image: str,
+        model_path: str,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        guidance_scale: int,
+        num_inference_step: int,
+        seed_generator=0,
+    ):
+        image = pil_image["image"].convert("RGB").resize((512, 512))
+        mask_image = pil_image["mask"].convert("RGB").resize((512, 512))
+        pipe = self.load_model(model_path)
+
+        if seed_generator == 0:
+            random_seed = torch.randint(0, 1000000, (1,))
+            generator = torch.manual_seed(random_seed)
+        else:
+            generator = torch.manual_seed(seed_generator)
+
+        output = pipe(
+            prompt=prompt,
+            image=image,
+            mask_image=mask_image,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_images_per_prompt,
+            num_inference_steps=num_inference_step,
+            guidance_scale=guidance_scale,
+            generator=generator,
+        ).images
+
+        return output
+
+    def app():
+        with gr.Blocks():
+            with gr.Row():
+                with gr.Column():
+                    stable_diffusion_inpaint_image_file = gr.Image(
+                        source="upload",
+                        tool="sketch",
+                        elem_id="image_upload",
+                        type="pil",
+                        label="Upload",
+                    ).style(height=260)
+
+                    stable_diffusion_inpaint_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Prompt",
+                        show_label=False,
+                    )
+
+                    stable_diffusion_inpaint_negative_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Negative Prompt",
+                        show_label=False,
+                    )
+                    stable_diffusion_inpaint_model_id = gr.Dropdown(
+                        choices=stable_inpiant_model_list,
+                        value=stable_inpiant_model_list[0],
+                        label="Inpaint Model Id",
+                    )
+                    with gr.Row():
+                        with gr.Column():
+                            stable_diffusion_inpaint_guidance_scale = gr.Slider(
+                                minimum=0.1,
+                                maximum=15,
+                                step=0.1,
+                                value=7.5,
+                                label="Guidance Scale",
+                            )
+
+                            stable_diffusion_inpaint_num_inference_step = (
+                                gr.Slider(
+                                    minimum=1,
+                                    maximum=100,
+                                    step=1,
+                                    value=50,
+                                    label="Num Inference Step",
+                                )
+                            )
+
+                        with gr.Row():
+                            with gr.Column():
+                                stable_diffusion_inpiant_num_images_per_prompt = gr.Slider(
+                                    minimum=1,
+                                    maximum=10,
+                                    step=1,
+                                    value=1,
+                                    label="Number Of Images",
+                                )
+                                stable_diffusion_inpaint_seed_generator = (
+                                    gr.Slider(
+                                        minimum=0,
+                                        maximum=1000000,
+                                        step=1,
+                                        value=0,
+                                        label="Seed(0 for random)",
+                                    )
+                                )
+
+                    stable_diffusion_inpaint_predict = gr.Button(
+                        value="Generator"
+                    )
+
+                with gr.Column():
+                    output_image = gr.Gallery(
+                        label="Generated images",
+                        show_label=False,
+                        elem_id="gallery",
+                    ).style(grid=(1, 2))
+
+            stable_diffusion_inpaint_predict.click(
+                fn=StableDiffusionInpaintGenerator().generate_image,
+                inputs=[
+                    stable_diffusion_inpaint_image_file,
+                    stable_diffusion_inpaint_model_id,
+                    stable_diffusion_inpaint_prompt,
+                    stable_diffusion_inpaint_negative_prompt,
+                    stable_diffusion_inpiant_num_images_per_prompt,
+                    stable_diffusion_inpaint_guidance_scale,
+                    stable_diffusion_inpaint_num_inference_step,
+                    stable_diffusion_inpaint_seed_generator,
+                ],
+                outputs=[output_image],
+            )

diffusion_webui/diffusion_models/text2img_app.py

@@ -0,0 +1,166 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionPipeline
+
+from diffusion_webui.utils.model_list import stable_model_list
+from diffusion_webui.utils.scheduler_list import (
+    SCHEDULER_MAPPING,
+    get_scheduler,
+)
+
+
+class StableDiffusionText2ImageGenerator:
+    def __init__(self):
+        self.pipe = None
+
+    def load_model(
+        self,
+        model_path,
+        scheduler,
+    ):
+        if self.pipe is None:
+            self.pipe = StableDiffusionPipeline.from_pretrained(
+                model_path, safety_checker=None, torch_dtype=torch.float16
+            )
+
+        self.pipe = get_scheduler(pipe=self.pipe, scheduler=scheduler)
+        self.pipe.to("cuda")
+        self.pipe.enable_xformers_memory_efficient_attention()
+
+        return self.pipe
+
+    def generate_image(
+        self,
+        model_path: str,
+        prompt: str,
+        negative_prompt: str,
+        num_images_per_prompt: int,
+        scheduler: str,
+        guidance_scale: int,
+        num_inference_step: int,
+        height: int,
+        width: int,
+        seed_generator=0,
+    ):
+        pipe = self.load_model(
+            model_path=model_path,
+            scheduler=scheduler,
+        )
+        if seed_generator == 0:
+            random_seed = torch.randint(0, 1000000, (1,))
+            generator = torch.manual_seed(random_seed)
+        else:
+            generator = torch.manual_seed(seed_generator)
+
+        images = pipe(
+            prompt=prompt,
+            height=height,
+            width=width,
+            negative_prompt=negative_prompt,
+            num_images_per_prompt=num_images_per_prompt,
+            num_inference_steps=num_inference_step,
+            guidance_scale=guidance_scale,
+            generator=generator,
+        ).images
+
+        return images
+
+    def app():
+        with gr.Blocks():
+            with gr.Row():
+                with gr.Column():
+                    text2image_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Prompt",
+                        show_label=False,
+                    )
+
+                    text2image_negative_prompt = gr.Textbox(
+                        lines=1,
+                        placeholder="Negative Prompt",
+                        show_label=False,
+                    )
+                    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_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_num_images_per_prompt = gr.Slider(
+                                minimum=1,
+                                maximum=30,
+                                step=1,
+                                value=1,
+                                label="Number Of Images",
+                            )
+                        with gr.Row():
+                            with gr.Column():
+                                text2image_scheduler = gr.Dropdown(
+                                    choices=list(SCHEDULER_MAPPING.keys()),
+                                    value=list(SCHEDULER_MAPPING.keys())[0],
+                                    label="Scheduler",
+                            )
+
+                                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=512,
+                                    label="Image Width",
+                                )
+                                text2image_seed_generator = gr.Slider(
+                                    label="Seed(0 for random)",
+                                    minimum=0,
+                                    maximum=1000000,
+                                    value=0,
+                                )
+                    text2image_predict = gr.Button(value="Generator")
+
+                with gr.Column():
+                    output_image = gr.Gallery(
+                        label="Generated images",
+                        show_label=False,
+                        elem_id="gallery",
+                    ).style(grid=(1, 2), height=200)
+
+            text2image_predict.click(
+                fn=StableDiffusionText2ImageGenerator().generate_image,
+                inputs=[
+                    text2image_model_path,
+                    text2image_prompt,
+                    text2image_negative_prompt,
+                    text2image_num_images_per_prompt,
+                    text2image_scheduler,
+                    text2image_guidance_scale,
+                    text2image_num_inference_step,
+                    text2image_height,
+                    text2image_width,
+                    text2image_seed_generator,
+                ],
+                outputs=output_image,
+            )

diffusion_webui/utils/data_utils.py

@@ -0,0 +1,12 @@
+from PIL import Image
+
+
+def image_grid(imgs, rows, cols):
+    assert len(imgs) == rows * cols
+
+    w, h = imgs[0].size
+    grid = Image.new("RGB", size=(cols * w, rows * h))
+
+    for i, img in enumerate(imgs):
+        grid.paste(img, box=(i % cols * w, i // cols * h))
+    return grid

diffusion_webui/utils/model_list.py

@@ -0,0 +1,36 @@
+stable_model_list = [
+    "runwayml/stable-diffusion-v1-5",
+    "stabilityai/stable-diffusion-2-1",
+    "prompthero/openjourney-v4",
+    "dreamlike-art/dreamlike-diffusion-1.0",
+]
+
+stable_inpiant_model_list = [
+    "stabilityai/stable-diffusion-2-inpainting",
+    "runwayml/stable-diffusion-inpainting",
+    "saik0s/realistic_vision_inpainting",
+]
+
+controlnet_model_list = [
+    #"lllyasviel/sd-controlnet-canny",
+    "lllyasviel/control_v11p_sd15_canny",
+    "thibaud/controlnet-sd21-canny-diffusers",
+    #"lllyasviel/sd-controlnet-depth",
+    "lllyasviel/control_v11f1p_sd15_depth",
+    "thibaud/controlnet-sd21-depth-diffusers",
+    #"lllyasviel/sd-controlnet-openpose",
+    "lllyasviel/control_v11p_sd15_openpose",
+    "thibaud/controlnet-sd21-openpose-diffusers",
+    #"lllyasviel/sd-controlnet-hed",
+    "thibaud/controlnet-sd21-hed-diffusers",
+    #"lllyasviel/sd-controlnet-scribble",
+    "lllyasviel/control_v11p_sd15_scribble",
+    "thibaud/controlnet-sd21-scribble-diffusers",
+    #"lllyasviel/sd-controlnet-mlsd",
+    "lllyasviel/control_v11p_sd15_mlsd",
+    "lllyasviel/control_v11e_sd15_shuffle",
+    "lllyasviel/control_v11e_sd15_ip2p",
+    "lllyasviel/control_v11p_sd15_lineart",
+    "lllyasviel/control_v11p_sd15s2_lineart_anime",
+    "lllyasviel/control_v11p_sd15_softedge",
+]

diffusion_webui/utils/preprocces_utils.py

@@ -0,0 +1,32 @@
+from controlnet_aux import (
+    CannyDetector,
+    ContentShuffleDetector,
+    HEDdetector,
+    LineartAnimeDetector,
+    LineartDetector,
+    MediapipeFaceDetector,
+    MidasDetector,
+    MLSDdetector,
+    NormalBaeDetector,
+    OpenposeDetector,
+    PidiNetDetector,
+    SamDetector,
+    ZoeDetector,
+)
+
+PREPROCCES_DICT = {
+    "Hed": HEDdetector.from_pretrained("lllyasviel/Annotators"),
+    "Midas": MidasDetector.from_pretrained("lllyasviel/Annotators"),
+    "MLSD": MLSDdetector.from_pretrained("lllyasviel/Annotators"),
+    "Openpose": OpenposeDetector.from_pretrained("lllyasviel/Annotators"),
+    "PidiNet": PidiNetDetector.from_pretrained("lllyasviel/Annotators"),
+    "NormalBae": NormalBaeDetector.from_pretrained("lllyasviel/Annotators"),
+    "Lineart": LineartDetector.from_pretrained("lllyasviel/Annotators"),
+    "LineartAnime": LineartAnimeDetector.from_pretrained(
+        "lllyasviel/Annotators"
+    ),
+    "Zoe": ZoeDetector.from_pretrained("lllyasviel/Annotators"),
+    "Canny": CannyDetector(),
+    "ContentShuffle": ContentShuffleDetector(),
+    "MediapipeFace": MediapipeFaceDetector(),
+}

diffusion_webui/utils/scheduler_list.py

@@ -0,0 +1,56 @@
+from diffusers import (
+    DDIMInverseScheduler,
+    DDIMScheduler,
+    DDPMScheduler,
+    DEISMultistepScheduler,
+    DPMSolverMultistepInverseScheduler,
+    DPMSolverMultistepScheduler,
+    DPMSolverSinglestepScheduler,
+    EulerAncestralDiscreteScheduler,
+    EulerDiscreteScheduler,
+    HeunDiscreteScheduler,
+    IPNDMScheduler,
+    KarrasVeScheduler,
+    KDPM2AncestralDiscreteScheduler,
+    KDPM2DiscreteScheduler,
+    PNDMScheduler,
+    RePaintScheduler,
+    SchedulerMixin,
+    ScoreSdeVeScheduler,
+    UnCLIPScheduler,
+    UniPCMultistepScheduler,
+    VQDiffusionScheduler,
+)
+
+SCHEDULER_MAPPING = {
+    "DDIM": DDIMScheduler,
+    "DDIMInverse": DDIMInverseScheduler,
+    "DDPMScheduler": DDPMScheduler,
+    "DEISMultistep": DEISMultistepScheduler,
+    "DPMSolverMultistepInverse": DPMSolverMultistepInverseScheduler,
+    "DPMSolverMultistep": DPMSolverMultistepScheduler,
+    "DPMSolverSinglestep": DPMSolverSinglestepScheduler,
+    "EulerAncestralDiscrete": EulerAncestralDiscreteScheduler,
+    "EulerDiscrete": EulerDiscreteScheduler,
+    "HeunDiscrete": HeunDiscreteScheduler,
+    "IPNDMScheduler": IPNDMScheduler,
+    "KarrasVe": KarrasVeScheduler,
+    "KDPM2AncestralDiscrete": KDPM2AncestralDiscreteScheduler,
+    "KDPM2Discrete": KDPM2DiscreteScheduler,
+    "PNDMScheduler": PNDMScheduler,
+    "RePaint": RePaintScheduler,
+    "ScoreSdeVe": ScoreSdeVeScheduler,
+    "UnCLIP": UnCLIPScheduler,
+    "UniPCMultistep": UniPCMultistepScheduler,
+    "VQDiffusion": VQDiffusionScheduler,
+}
+
+
+def get_scheduler(pipe, scheduler):
+    if scheduler in SCHEDULER_MAPPING:
+        SchedulerClass = SCHEDULER_MAPPING[scheduler]
+        pipe.scheduler = SchedulerClass.from_config(pipe.scheduler.config)
+    else:
+        raise ValueError(f"Invalid scheduler name {scheduler}")
+
+    return pipe

requirements.txt

@@ -1,8 +1,9 @@
 transformers 
 bitsandbytes==0.35.0 
 xformers 
-controlnet_aux==0.0.3
-diffusers
+controlnet_aux 
+git+https://github.com/huggingface/diffusers
 imageio
-triton
-codeformer-pip
+gradio
+controlnet_aux
+mediapipe