Create app.py

app.py

@@ -1,154 +1,85 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
+from diffusers import StableDiffusionPipeline
+import gradio as gr
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    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: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        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.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # 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=0.0,  # 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=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
+# 选择一个文生图模型
+MODEL_NAME = "runwayml/stable-diffusion-v1-5"
+
+def load_model():
+    """
+    自动下载并加载文生图模型
+    """
+    try:
+        # 使用 torch.float16 减少显存占用
+        pipe = StableDiffusionPipeline.from_pretrained(
+            MODEL_NAME, 
+            torch_dtype=torch.float16
+        )
+        
+        # 如果有GPU，移动模型到GPU
+        if torch.cuda.is_available():
+            pipe = pipe.to("cuda")
+        
+        return pipe
+    except Exception as e:
+        print(f"模型加载错误: {e}")
+        return None
+
+# 全局模型变量
+generation_pipe = load_model()
+
+def generate_image(prompt, negative_prompt="", steps=50, guidance_scale=7.5):
+    """
+    根据文本提示生成图像
+    
+    :param prompt: 图像生成提示词
+    :param negative_prompt: 负面提示词
+    :param steps: 生成步数
+    :param guidance_scale: 引导强度
+    :return: 生成的图像
+    """
+    if generation_pipe is None:
+        return "模型加载失败"
+    
+    try:
+        # 生成图像
+        image = generation_pipe(
+            prompt, 
+            negative_prompt=negative_prompt,
+            num_inference_steps=steps,
+            guidance_scale=guidance_scale
+        ).images[0]
+        
+        return image
+    except Exception as e:
+        print(f"图像生成错误: {e}")
+        return None
+
+# 创建 Gradio 界面
+def create_interface():
+    iface = gr.Interface(
+        fn=generate_image,
         inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
+            gr.Textbox(label="图像描述 (Prompt)"),
+            gr.Textbox(label="负面描述 (Negative Prompt)", value=""),
+            gr.Slider(minimum=10, maximum=100, value=50, label="生成步数"),
+            gr.Slider(minimum=1, maximum=15, value=7.5, label="引导强度")
         ],
-        outputs=[result, seed],
+        outputs=gr.Image(label="生成的图像"),
+        title="文生图生成",
+        description="使用 Stable Diffusion 从文本生成图像"
     )
+    return iface
 
+# 启动应用
 if __name__ == "__main__":
-    demo.launch()
+    # 检查并提示模型加载状态
+    if generation_pipe is None:
+        print("警告：模型加载失败，应用可能无法正常工作")
+    
+    # 启动 Gradio 界面
+    interface = create_interface()
+    interface.launch(
+        # 如果需要公开访问，取消注释下面的行
+        # share=True
+    )