Update app.py

app.py

@@ -1,154 +1,65 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 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;
+from diffusers import StableDiffusionPipeline
+from datetime import datetime
+
+# Load the model
+model_id = "stabilityai/stable-diffusion-2"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+# Keep image history
+image_history = []
+
+# Style templates
+STYLE_TEMPLATES = {
+    "Photo": "highly detailed, realistic photo, natural lighting",
+    "Anime": "anime style, vibrant colors, line art, cel shading",
+    "Oil Painting": "oil painting style, brush strokes, classic fine art"
 }
-"""
-
-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,
-            )
+def enhance_prompt(prompt, style):
+    style_suffix = STYLE_TEMPLATES.get(style, "")
+    return f"{prompt}, {style_suffix}"
 
-            run_button = gr.Button("Run", scale=0, variant="primary")
+def generate_image(prompt, style):
+    if not prompt.strip():
+        return None, image_history
 
-        result = gr.Image(label="Result", show_label=False)
+    final_prompt = enhance_prompt(prompt, style)
+    image = pipe(final_prompt).images[0]
+    
+    # Add to history
+    timestamp = datetime.now().strftime("%H:%M:%S")
+    caption = f"{style} - {timestamp}"
+    image_history.append((image, caption))
+    
+    return image, image_history[-5:]  # show latest 5 only
 
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
+def clear_history():
+    global image_history
+    image_history = []
+    return None, []
 
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🎨 Realistic Text-to-Image Generator")
+    gr.Markdown("Powered by **Stable Diffusion 2** | Now with style presets, prompt enhancer, and image history!")
 
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+    with gr.Row():
+        prompt = gr.Textbox(label="Enter your prompt", placeholder="e.g., A golden retriever in the snow")
+        style = gr.Dropdown(["Photo", "Anime", "Oil Painting"], label="Choose Style", value="Photo")
 
-            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
-                )
+    with gr.Row():
+        generate_btn = gr.Button("🎨 Generate Image")
+        clear_btn = gr.Button("🧹 Clear History")
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+    output_image = gr.Image(label="Generated Image", type="pil")
 
-            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
-                )
+    gallery = gr.Gallery(label="🖼️ Image History (last 5)", columns=3, object_fit="contain")
 
-                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
-                )
+    generate_btn.click(generate_image, inputs=[prompt, style], outputs=[output_image, gallery])
+    clear_btn.click(clear_history, outputs=[output_image, gallery])
 
-        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],
-    )
+demo.launch()
 
-if __name__ == "__main__":
-    demo.launch()