app3.py

# import torch
# import random
# import numpy as np
# import gradio as gr
# from pytorch_lightning import seed_everything
# from annotator.util import resize_image, HWC3
# from diffusers import StableDiffusionControlNetPipeline, ControlNetModel

# # # Load the controlnet model
# # controlnet = ControlNetModel.from_pretrained("CompVis/controlnet")

# # # Load the pipeline
# # pipe = StableDiffusionControlNetPipeline.from_pretrained(
# #     "CompVis/stable-diffusion-v1-4",
# #     controlnet=controlnet
# # ).to("cuda")
# controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
# pipe = StableDiffusionControlNetPipeline.from_pretrained(
#     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
# )

# def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, low_threshold, high_threshold):
#     with torch.no_grad():
#         img = resize_image(HWC3(input_image), image_resolution)
        
#         if seed == -1:
#             seed = random.randint(0, 65535)
#         seed_everything(seed)

#         # Generate images using the pipeline
#         generator = torch.Generator("cuda").manual_seed(seed)
#         images = pipe(prompt=prompt + ', ' + a_prompt, num_inference_steps=ddim_steps, guidance_scale=scale, generator=generator, num_images_per_prompt=num_samples).images

#         results = [np.array(image) for image in images]
#     return results

# block = gr.Blocks().queue()
# with block:
#     with gr.Row():
#         gr.Markdown("## Scene Diffusion with ControlNet")
#     with gr.Row():
#         with gr.Column():
#             input_image = gr.Image(label="Image")
#             prompt = gr.Textbox(label="Prompt")
#             a_prompt = gr.Textbox(label="Additional Prompt")
#             n_prompt = gr.Textbox(label="Negative Prompt")
#             num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
#             image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=64)
#             ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
#             guess_mode = gr.Checkbox(label='Guess Mode', value=False)
#             strength = gr.Slider(label="Strength", minimum=0.0, maximum=1.0, value=0.5, step=0.1)
#             scale = gr.Slider(label="Scale", minimum=0.1, maximum=30.0, value=10.0, step=0.1)
#             seed = gr.Slider(label="Seed", minimum=0, maximum=10000, value=42, step=1)
#             eta = gr.Slider(label="ETA", minimum=0.0, maximum=1.0, value=0.0, step=0.1)
#             low_threshold = gr.Slider(label="Canny Low Threshold", minimum=1, maximum=255, value=100, step=1)
#             high_threshold = gr.Slider(label="Canny High Threshold", minimum=1, maximum=255, value=200, step=1)
#             submit = gr.Button("Generate")
#         with gr.Column():
#             output_image = gr.Gallery(label='Output', show_label=False, elem_id="gallery")
#     submit.click(fn=process, inputs=[input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, strength, scale, seed, eta, low_threshold, high_threshold], outputs=output_image)

# demo = block
# demo.launch()
import torch
from diffusers import StableDiffusionControlNetPipeline
from diffusers import ControlNetModel
import gradio as gr
from PIL import Image
import numpy as np

# 初始化 ControlNet 模型和 Stable Diffusion Pipeline
controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
pipeline = StableDiffusionControlNetPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", controlnet=controlnet)

# 定义图像生成函数
def generate_image(prompt: str, input_image: Image.Image):
    # 可以在这里根据传入的图像做一些预处理（例如，使用控制网络或图像生成模型）
    
    # 将输入图像转换为合适的格式
    input_image = input_image.convert("RGB")
    
    # 生成图像
    result_image = pipeline(prompt=prompt, init_image=input_image, strength=0.75).images[0]
    return result_image

# 创建 Gradio 界面
iface = gr.Interface(
    fn=generate_image,
    inputs=[
        gr.Textbox(label="Enter a prompt", placeholder="e.g. a futuristic city at sunset"),  # 提示框
        gr.Image(label="Upload an Image", type="pil")  # 图像上传框
    ],
    outputs=gr.Image(label="Generated Image"),  # 输出生成的图像
    live=True
)

# 启动 Gradio 应用
iface.launch(share=True)