Update app.py

app.py

@@ -1,94 +1,87 @@
 import gradio as gr
 import numpy as np
 import random
+#import spaces #[uncomment to use ZeroGPU]
 from diffusers import DiffusionPipeline
 import torch
 
-# Check if CUDA is available
 device = "cuda" if torch.cuda.is_available() else "cpu"
+model_repo_id = "stabilityai/sdxl-turbo" #Replace to the model you would like to use
 
-# Define the model you want to use (black-forest-labs/FLUX.1-dev)
-model_repo_id = "black-forest-labs/FLUX.1-dev"
+if torch.cuda.is_available():
+    torch_dtype = torch.float16
+else:
+    torch_dtype = torch.float32
 
-# Set the appropriate torch dtype depending on the available hardware
-torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-
-# Load the model
 pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
 pipe = pipe.to(device)
 
-# Constants for seed and image size
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-# Function to perform inference using the model
+#@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 is checked, generate a random seed
+
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
-    
-    # Set the seed for reproducibility
+        
     generator = torch.Generator().manual_seed(seed)
     
-    # Generate the image based on the prompt
     image = pipe(
-        prompt=prompt, 
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale, 
-        num_inference_steps=num_inference_steps, 
-        width=width, 
-        height=height,
-        generator=generator
+        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
 
-# Example prompts for testing the model
 examples = [
-    "A futuristic city skyline at sunset",
-    "A cat riding a bicycle in space",
-    "A surreal painting of a dreamlike forest",
+    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+    "An astronaut riding a green horse",
+    "A delicious ceviche cheesecake slice",
 ]
 
-# Custom CSS for styling the UI
-css = """
+css="""
 #col-container {
     margin: 0 auto;
     max-width: 640px;
 }
 """
 
-# Create the Gradio interface
 with gr.Blocks(css=css) as demo:
     
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""
-        # Text-to-Image Generation using FLUX.1-dev Model
+        # Text-to-Image Gradio Template
         """)
         
-        # Input row for prompt and run button
         with gr.Row():
+            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
                 max_lines=1,
-                placeholder="Enter your text prompt",
+                placeholder="Enter your prompt",
                 container=False,
             )
-            run_button = gr.Button("Generate Image", scale=0)
+            
+            run_button = gr.Button("Run", scale=0)
         
-        # Output for the generated image
-        result = gr.Image(label="Generated Image", show_label=False)
+        result = gr.Image(label="Result", show_label=False)
 
-        # Accordion for advanced settings
         with gr.Accordion("Advanced Settings", open=False):
+            
             negative_prompt = gr.Text(
-                label="Negative Prompt",
+                label="Negative prompt",
                 max_lines=1,
-                placeholder="Enter a negative prompt (optional)",
+                placeholder="Enter a negative prompt",
                 visible=False,
             )
+            
             seed = gr.Slider(
                 label="Seed",
                 minimum=0,
@@ -96,55 +89,54 @@ with gr.Blocks(css=css) as demo:
                 step=1,
                 value=0,
             )
-            randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
-
-            # Sliders for width and height of the output image
+            
+            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=512, # Default width value
+                    value=1024, #Replace with defaults that work for your model
                 )
+                
                 height = gr.Slider(
                     label="Height",
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=512, # Default height value
+                    value=1024, #Replace with defaults that work for your model
                 )
             
-            # Sliders for guidance scale and number of inference steps
             with gr.Row():
+                
                 guidance_scale = gr.Slider(
-                    label="Guidance Scale",
+                    label="Guidance scale",
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
-                    value=7.5, # Default value that works for most models
+                    value=0.0, #Replace with defaults that work for your model
                 )
+                
                 num_inference_steps = gr.Slider(
-                    label="Number of Inference Steps",
+                    label="Number of inference steps",
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=25, # Default number of steps for better image quality
+                    value=2, #Replace with defaults that work for your model
                 )
-
-        # Example inputs for quick testing
+        
         gr.Examples(
-            examples=examples,
-            inputs=[prompt]
+            examples = examples,
+            inputs = [prompt]
         )
-
-    # Set up triggers for image generation when prompt is submitted or button is clicked
     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]
+        fn = infer,
+        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs = [result, seed]
     )
 
-# Launch the Gradio app
-demo.queue().launch()
+demo.queue().launch()