Upload 2 files

app.py

@@ -1,154 +1,68 @@
-import gradio as gr
-import numpy as np
-import random
 
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+import gradio as gr
+import pandas as pd
 import torch
-
-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,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+from diffusers import StableDiffusionXLPipeline
+from PIL import Image
+import os
+import zipfile
+
+# 加载模型（GPU环境）
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16,
+    variant="fp16"
+).to("cuda")
+
+# 文本模板生成函数
+def generate_text(prompt):
+    return f"这是一幅描绘：{prompt} 的画面，小朋友可以根据图像发挥想象力哦！"
+
+# 模式一：处理CSV并生成图文ZIP
+def process_csv(file):
+    df = pd.read_csv(file.name)
+    output_dir = "output"
+    os.makedirs(output_dir, exist_ok=True)
+
+    for idx, row in df.iterrows():
+        prompt = row["prompt"]
+        image = pipe(prompt=prompt).images[0]
+        image_path = os.path.join(output_dir, f"image_{idx+1}.png")
+        image.save(image_path)
+
+        text = generate_text(prompt)
+        text_path = os.path.join(output_dir, f"text_{idx+1}.txt")
+        with open(text_path, "w") as f:
+            f.write(text)
+
+    # 打包ZIP
+    zip_path = "output.zip"
+    with zipfile.ZipFile(zip_path, "w") as zipf:
+        for file_name in os.listdir(output_dir):
+            file_path = os.path.join(output_dir, file_name)
+            zipf.write(file_path, arcname=file_name)
+    return zip_path
+
+# 模式二：文本转图片
+def text_to_image(prompt):
+    image = pipe(prompt=prompt).images[0]
+    return image
+
+# Gradio界面
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 AI 图文生成器 - 批量 & 单图模式")
+
+    with gr.Tab("📂 批量生成（上传CSV）"):
+        csv_input = gr.File(label="上传CSV文件", file_types=[".csv"])
+        csv_output = gr.File(label="生成图文ZIP包")
+        csv_btn = gr.Button("开始生成")
+        csv_btn.click(fn=process_csv, inputs=csv_input, outputs=csv_output)
+
+    with gr.Tab("🖼️ 单图生成（文本转图片）"):
+        prompt_input = gr.Textbox(label="输入提示词", placeholder="比如：一只飞翔在太空的小猫咪")
+        image_output = gr.Image(label="生成的图像", type="pil")
+        single_btn = gr.Button("立即生成")
+        single_btn.click(fn=text_to_image, inputs=prompt_input, outputs=image_output)
 
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1,6 +1,9 @@
-accelerate
-diffusers
-invisible_watermark
-torch
-transformers
-xformers
+
+gradio
+pandas
+torch==2.1.0
+diffusers==0.27.2
+transformers==4.40.0
+accelerate==0.28.0
+safetensors
+pillow