Update app.py

app.py

@@ -1,96 +1,66 @@
 import gradio as gr
-import random
-import torch
-from diffusers import DiffusionPipeline
 
-# Device setup
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id_turbo = "stabilityai/sdxl-turbo"  # Stability AI Model
-pipe_turbo = DiffusionPipeline.from_pretrained(model_repo_id_turbo, torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32).to(device)
-
-# Placeholder for ZB-Tech model
-def load_zb_model():
-    return gr.Interface.load("models/ZB-Tech/Text-to-Image")
-
-# Inference function
-def custom_infer(
-    model_choice, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps
-):
-    # Load the selected model
-    if model_choice == "Faster image generation (suitable for CPUs)":
-        model = load_zb_model()
-        return model(prompt)
-    else:
-        default_negative_prompt = "no watermark, hezzy, blurry"
-        combined_negative_prompt = f"{default_negative_prompt}, {negative_prompt}" if negative_prompt else default_negative_prompt
-        
-        if randomize_seed:
-            seed = random.randint(0, np.iinfo(np.int32).max)
-        
-        generator = torch.Generator().manual_seed(seed)
-        image = pipe_turbo(
-            prompt=prompt,
-            negative_prompt=combined_negative_prompt,
-            guidance_scale=guidance_scale,
-            num_inference_steps=num_inference_steps,
-            width=width,
-            height=height,
-            generator=generator,
-        ).images[0]
-        return image, seed
-
-# CSS for centering UI
+# CSS for aligning the UI elements in the middle
 css = """
 #col-container {
-    display: flex;
-    flex-direction: column;
-    align-items: center;
-    justify-content: center;
-    text-align: center;
     margin: 0 auto;
+    max-width: 640px;
+    text-align: center;
 }
 """
 
+# Maximum image size
+MAX_IMAGE_SIZE = 1024
+
+# Load the ZB-Tech/Text-to-Image model
+def infer(prompt, height, width):
+    model = gr.Interface.load("models/ZB-Tech/Text-to-Image")
+    return model(prompt, height=height, width=width)
+
 # Gradio app
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        # App name and description
+        # Title and description
         gr.Markdown(
             """
             # AI-Powered Text-to-Image Generator  
-            *Generate stunning images from text prompts using advanced AI models.*
+            *Generate stunning images from text prompts using the ZB-Tech/Text-to-Image model.*
             """
         )
 
-        # Dropdown for model selection
-        model_choice = gr.Dropdown(
-            label="Select Model",
-            choices=[
-                "Faster image generation (suitable for CPUs)",
-                "More customizable option (slower, suitable for GPUs)"
-            ],
-            value="Faster image generation (suitable for CPUs)",
+        # Input: Prompt
+        prompt = gr.Textbox(
+            label="Prompt",
+            placeholder="Enter your prompt here...",
+            lines=2,
         )
 
-        # Input section
-        prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...")
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Textbox(label="Negative Prompt", placeholder="Enter a negative prompt here...")
-            seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, value=0)
-            randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
-            width = gr.Slider(label="Width", minimum=256, maximum=1024, step=32, value=512)
-            height = gr.Slider(label="Height", minimum=256, maximum=1024, step=32, value=512)
-            guidance_scale = gr.Slider(label="Guidance Scale", minimum=0.0, maximum=10.0, step=0.1, value=7.5)
-            num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=50, step=1, value=25)
+        # Input: Height and Width sliders
+        height = gr.Slider(
+            label="Height",
+            minimum=256,
+            maximum=MAX_IMAGE_SIZE,
+            step=32,
+            value=1024,
+        )
 
-        # Output section
-        result = gr.Image(label="Generated Image", type="pil")
-        gr.Button("Generate").click(
-            custom_infer,
-            inputs=[model_choice, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-            outputs=result
+        width = gr.Slider(
+            label="Width",
+            minimum=256,
+            maximum=MAX_IMAGE_SIZE,
+            step=32,
+            value=1024,
         )
 
-# Launch app
+        # Output: Generated Image
+        result = gr.Image(label="Generated Image", type="pil")
+
+        # Generate Button
+        generate_button = gr.Button("Generate")
+
+        # Button action: Call infer function
+        generate_button.click(infer, inputs=[prompt, height, width], outputs=result)
+
+# Launch the app
 if __name__ == "__main__":
     demo.launch()