blocks/img2img.py

import gradio as gr
import torch
from diffusers import StableDiffusionImg2ImgPipeline
from .utils.schedulers import SCHEDULER_LIST, get_scheduler_list
from .utils.prompt2prompt import generate
from .utils.device import get_device
from PIL import Image
from .download import get_share_js, get_community_loading_icon, CSS

IMG2IMG_MODEL_LIST = {
    "StableDiffusion 1.5" : "runwayml/stable-diffusion-v1-5",
    "StableDiffusion 2.1" : "stabilityai/stable-diffusion-2-1",
    "OpenJourney v4" : "prompthero/openjourney-v4",
    "DreamLike 1.0" : "dreamlike-art/dreamlike-diffusion-1.0",
    "DreamLike 2.0" : "dreamlike-art/dreamlike-photoreal-2.0"
}

class StableDiffusionImage2ImageGenerator:
    def __init__(self):
        self.pipe = None

    def load_model(self, model_path, scheduler):
        model_path = IMG2IMG_MODEL_LIST[model_path]
        if self.pipe is None:
            self.pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
                model_path, safety_checker=None, torch_dtype=torch.float32
            )

        device = get_device()
        self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)

        self.pipe.to(device)
        #self.pipe.enable_attention_slicing()

        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():
        demo = gr.Blocks(css=CSS)
        with demo:
            with gr.Row():
                with gr.Column():
                    image2image_image_file = gr.Image(
                        type="filepath", label="Upload",elem_id="image-upload-img2img"
                    ).style(height=260)

                    image2image_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Prompt",
                        show_label=False,
                        elem_id="prompt-text-input-img2img",
                        value=''
                    )

                    image2image_negative_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Negative Prompt",
                        show_label=False,
                        elem_id = "negative-prompt-text-input-img2img",
                        value=''
                    )

                    # add button for generating a prompt from the prompt
                    image2image_generate_prompt_button = gr.Button(
                        label="Generate Prompt",
                        type="primary",
                        align="center",
                        value = "Generate Prompt"
                    )

                    # show a text box with the generated prompt
                    image2image_generated_prompt = gr.Textbox(
                        lines=1,
                        placeholder="Generated Prompt",
                        show_label=False,
                    )

                    with gr.Row():
                        with gr.Column():
                            image2image_model_path = gr.Dropdown(
                                choices=list(IMG2IMG_MODEL_LIST.keys()),
                                value=list(IMG2IMG_MODEL_LIST.keys())[0],
                                label="Imaget2Image Model Selection",
                                elem_id="model-dropdown-img2img",
                            )

                            image2image_guidance_scale = gr.Slider(
                                minimum=0.1,
                                maximum=15,
                                step=0.1,
                                value=7.5,
                                label="Guidance Scale",
                                elem_id = "guidance-scale-slider-img2img"
                            )

                            image2image_num_inference_step = gr.Slider(
                                minimum=1,
                                maximum=100,
                                step=1,
                                value=50,
                                label="Num Inference Step",
                                elem_id = "num-inference-step-slider-img2img"
                            )
                        with gr.Row():
                            with gr.Column():
                                image2image_scheduler = gr.Dropdown(
                                    choices=SCHEDULER_LIST,
                                    value=SCHEDULER_LIST[0],
                                    label="Scheduler",
                                    elem_id="scheduler-dropdown-img2img",
                                )
                                image2image_num_images_per_prompt = gr.Slider(
                                    minimum=1,
                                    maximum=30,
                                    step=1,
                                    value=1,
                                    label="Number Of Images",
                                )

                                image2image_seed_generator = gr.Slider(
                                    label="Seed(0 for random)",
                                    minimum=0,
                                    maximum=1000000,
                                    value=0,
                                    elem_id="seed-slider-img2img",
                                )

                    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))

                    with gr.Group(elem_id="container-advanced-btns"):
                        with gr.Group(elem_id="share-btn-container"):
                            community_icon_html, loading_icon_html = get_community_loading_icon("img2img")
                            community_icon = gr.HTML(community_icon_html)
                            loading_icon = gr.HTML(loading_icon_html)
                            share_button = gr.Button("Save artwork", elem_id="share-btn-img2img")

            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],
            )

            image2image_generate_prompt_button.click(
                fn=generate,
                inputs=[image2image_prompt],
                outputs=[image2image_generated_prompt],
            )


        return demo