Update app.py

app.py

@@ -1,51 +1,54 @@
 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
+# Device setup - CPU for now
+device = "cpu"
 
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
+# Model setup (replace with the model you want to use)
+model_repo_id = "KingNish/Realtime-FLUX"
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
+# CPU runs with float32 as float16 is typically for GPU
+torch_dtype = torch.float32
 
+# Load the model on CPU
+pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype).to(device)
+
+# Constants
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
+MAX_IMAGE_SIZE = 512  # Reduce size for CPU performance
 
-#@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)
+    generator = torch.manual_seed(seed)
     
+    # Generate image using the pipeline
     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
 
+# Sample prompts
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "Astronaut in a jungle, cold color palette, detailed, 8k",
+    "A robot playing a guitar in a futuristic city",
+    "A glowing blue cat sitting on a floating island"
 ]
 
-css="""
+# Gradio Interface
+css = """
 #col-container {
     margin: 0 auto;
     max-width: 640px;
@@ -55,31 +58,27 @@ css="""
 with gr.Blocks(css=css) as demo:
     
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        """)
-        
+        gr.Markdown("# Realtime-FLUX Text-to-Image Generator")
+
         with gr.Row():
-            
-            prompt = gr.Text(
+            prompt = gr.Textbox(
                 label="Prompt",
                 show_label=False,
                 max_lines=1,
-                placeholder="Enter your prompt",
+                placeholder="Describe the image you want to generate...",
                 container=False,
             )
             
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
+            run_button = gr.Button("Generate")
+
+        result = gr.Image(label="Generated Image", show_label=False)
 
         with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
+            negative_prompt = gr.Textbox(
+                label="Negative Prompt",
                 max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
+                placeholder="Enter a negative prompt (optional)",
+                visible=True,
             )
             
             seed = gr.Slider(
@@ -90,53 +89,51 @@ with gr.Blocks(css=css) as demo:
                 value=0,
             )
             
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
+            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
+                    value=384,  # Optimal for CPU
                 )
-                
                 height = gr.Slider(
                     label="Height",
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024, #Replace with defaults that work for your model
+                    value=384,  # Optimal for CPU
                 )
             
             with gr.Row():
-                
                 guidance_scale = gr.Slider(
-                    label="Guidance scale",
+                    label="Guidance Scale",
                     minimum=0.0,
                     maximum=10.0,
-                    step=0.1,
-                    value=0.0, #Replace with defaults that work for your model
+                    step=0.5,
+                    value=7.5,
                 )
                 
                 num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
+                    label="Inference Steps",
                     minimum=1,
-                    maximum=50,
+                    maximum=25,  # Keep lower for CPU performance
                     step=1,
-                    value=2, #Replace with defaults that work for your model
+                    value=15,  # Reasonable default for CPU
                 )
         
         gr.Examples(
-            examples = examples,
-            inputs = [prompt]
+            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]
+        fn=infer,
+        inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, seed]
     )
 
-demo.queue().launch()
+demo.queue().launch()