app.py

import gradio as gr
import numpy as np
import random
from typing import Optional

# import spaces #[uncomment to use ZeroGPU]
from diffusers import StableDiffusionPipeline, StableDiffusionControlNetPipeline
from diffusers import ControlNetModel
from peft import PeftModel, LoraConfig
from rembg import new_session, remove

from PIL import Image as PILImage
import cv2

import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

import os
# import torch

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024


CONTROL_MODE_MODEL = {
"Canny Ege Detection" : "lllyasviel/control_v11p_sd15_canny",
"Pixel to Pixel": "lllyasviel/control_v11e_sd15_ip2p",
"M-LSD Line detection" : "lllyasviel/control_v11p_sd15_mlsd",
"HED edge detection (soft edge)" : "lllyasviel/control_sd15_hed",
"Midas depth estimationn" : "lllyasviel/control_v11f1p_sd15_depth",
"Surface Normal Estimation" : "lllyasviel/control_v11p_sd15_normalbae",
"Scribble-Based Generation" : "lllyasviel/control_v11p_sd15_scribble",
"Semantic segmentation" : "lllyasviel/control_v11p_sd15_seg",
"OpenPose pose detection" : "lllyasviel/control_v11p_sd15_openpose",
"Line Art Generation": "lllyasviel/control_v11p_sd15_lineart",
}

# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt: str,
    negative_prompt : str,
    width,
    height,
    lscale=0.0,
    remove_background=False,
    controlnet_enabled=False,
    controlnet_strength=0.0,
    controlnet_mode=None,
    controlnet_image=None,
    ip_adapter_enabled=False,
    ip_adapter_scale=0.0,
    ip_adapter_image=None,
    model_id: Optional[str]  = "CompVis/stable-diffusion-v1-4",
    seed: Optional[int] = 42,
    guidance_scale : Optional[int] = 7,
    num_inference_steps : Optional[int] = 20,
    progress=gr.Progress(track_tqdm=True),
):

    generator = torch.Generator().manual_seed(seed)

    if controlnet_enabled:
        if not controlnet_image :
            raise ValueError("controlnet_enabled set to True, but controlnet_image not given")
        else:
            controlnet_model = ControlNetModel.from_pretrained(CONTROL_MODE_MODEL.get(controlnet_mode),torch_dtype=torch_dtype)
        if model_id == "SD-v1-5 + Lora" :
            pipe=StableDiffusionControlNetPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5",controlnet=controlnet_model, torch_dtype=torch_dtype)
            pipe.unet = PeftModel.from_pretrained(pipe.unet , "Emilichcka/diffusion_lora_funny_cat", subfolder="unet", torch_dtype=torch_dtype)
            pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder,"Emilichcka/diffusion_lora_funny_cat", subfolder="text_encoder", torch_dtype=torch_dtype)

        else:
            pipe=StableDiffusionControlNetPipeline.from_pretrained(model_id, controlnet=controlnet_model, torch_dtype=torch_dtype)
    else:
        if model_id == "SD-v1-5 + Lora" :
            pipe=StableDiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5",torch_dtype=torch_dtype)
            pipe.unet = PeftModel.from_pretrained(pipe.unet , "Emilichcka/diffusion_lora_funny_cat", subfolder="unet", torch_dtype=torch_dtype)
            pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder,"Emilichcka/diffusion_lora_funny_cat", subfolder="text_encoder", torch_dtype=torch_dtype)
        else:
            pipe=StableDiffusionPipeline.from_pretrained(model_id)

    if ip_adapter_enabled:
            ip_adapter_scale = float(ip_adapter_scale)
            pipe.load_ip_adapter("h94/IP-Adapter",subfolder="models", weight_name="ip-adapter-plus_sd15.bin", torch_dtype=torch_dtype)
            pipe.set_ip_adapter_scale(ip_adapter_scale)

    if controlnet_image!= None:
      controlnet_image = np.array(controlnet_image)

      low_threshold = 100
      high_threshold = 200

      controlnet_image = cv2.Canny(controlnet_image, low_threshold, high_threshold)
      controlnet_image = controlnet_image[:, :, None]
      controlnet_image = np.concatenate([controlnet_image, controlnet_image, controlnet_image], axis=2)
      controlnet_image = PILImage.fromarray(controlnet_image)

    pipe = pipe.to(device)


    image = pipe(
        prompt=prompt,
        image=controlnet_image,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
        cross_attention_kwargs={"scale": lscale},
        controlnet_conditioning_scale=controlnet_strength,
        ip_adapter_image=ip_adapter_image,
    ).images[0]

    if remove_background:
      image = remove(image)

    return image, seed


examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 880px;
}
"""

default_model_id_choice = [
    "stable-diffusion-v1-5/stable-diffusion-v1-5",
    "CompVis/stable-diffusion-v1-4",
    "SD-v1-5 + Lora",
    "nota-ai/bk-sdm-small",

]

def update_controlnet_visibility(controlnet_enabled):
    return gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled), gr.update(visible=controlnet_enabled)

def update_ip_adapter_visibility(ip_adapter_enabled):
    return gr.update(visible=ip_adapter_enabled), gr.update(visible=ip_adapter_enabled)

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template")

        with gr.Row():
            model_id = gr.Dropdown(
            label="Model Selection",
            choices=default_model_id_choice,
            value="SD-v1-5 + Lora",
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )

        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )

            run_button = gr.Button("Run", scale=0, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Row():
            remove_background = gr.Checkbox(label="Remove Background", value=False)
            controlnet_enabled = gr.Checkbox(label="Enable ControlNet", value=False)
            ip_adapter_enabled = gr.Checkbox(label="Enable IP-Adapter", value=False)

        with gr.Accordion("ControlNet Settings", open=False):
            gr.Markdown("Enable ControlNet to use settings", visible=True)
            with gr.Row():
                controlNet_strength = gr.Slider(
                    label="ControlNet scale",
                    minimum=0.0, maximum=1.0, step=0.05, value=0.75,
                    visible=False,
                    interactive=True,
                )

                controlNet_mode = gr.Dropdown(
                    label="ControlNet Mode",
                    choices=list(CONTROL_MODE_MODEL.keys()),
                    visible=False,
                    interactive=True,
                )

            controlNet_image = gr.Image(label="ControlNet Image", type="pil",
                                        interactive=True, visible=False)

        with gr.Accordion("IP-Adapter Settings", open=False):
            gr.Markdown("Enable IP-Adapter to use settings", visible=True)
            with gr.Row():
                ip_adapter_scale = gr.Slider(
                    label="IP-Adapter Scale",
                    minimum=0.0, maximum=2.0, step=0.05, value=1.0,
                    visible=False,
                    interactive=True,
                )

            ip_adapter_image = gr.Image(label="IP-Adapter Image", type="pil",interactive=True, visible=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
            )

            lora_scale = gr.Slider(
                label="LoRA Scale",
                minimum=0.0,
                maximum=2.0,
                step=0.1,
                value=1.0,
                info="Adjust the influence of the LoRA weights",
                interactive=True,
            )
            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=10.0,  # Replace with defaults that work for your model
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=30,  # Replace with defaults that work for your model
                )

        gr.Examples(examples=examples, inputs=[prompt])

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            width,
            height,
            lora_scale,
            remove_background,
            controlnet_enabled,
            controlNet_strength,
            controlNet_mode,
            controlNet_image,
            ip_adapter_enabled,
            ip_adapter_scale,
            ip_adapter_image,
            model_id,
            seed,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

    controlnet_enabled.change(
        fn=update_controlnet_visibility,
        inputs=[controlnet_enabled],
        outputs=[controlNet_strength, controlNet_mode, controlNet_image],
    )

    ip_adapter_enabled.change(
        fn=update_ip_adapter_visibility,
        inputs=[ip_adapter_enabled],
        outputs=[ip_adapter_scale, ip_adapter_image],
    )

if __name__ == "__main__":
    demo.launch(share=True)