Update app.py

app.py

@@ -1,146 +1,84 @@
-import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
+## app.py:
 import torch
+import gradio as gr
+from diffusers import StableDiffusionPipeline
+import requests
+from io import BytesIO
+import os
+from PIL import Image
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
 
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
+def translate_text(text, target_language='en'):
+    API_URL = "https://api-inference.huggingface.co/models/Helsinki-NLP/opus-mt-ar-en"
+    headers = {"Authorization": f"Bearer {os.getenv('API_TOKEN')}"}
+    response = requests.post(API_URL, headers=headers, json=text)
 
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+    if response.status_code == 200:
+        return response.json()[0]['translation_text']
 
-    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
+    else:
+        print("Failed to translate text:", response.text)
+        return text  # Return the original text if translation fails
 
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
+# Function to post data to an API and return response
+def query(payload, API_URL, headers):
+    response = requests.post(API_URL, headers=headers, json=payload)
+    return response.content
 
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
+# Function to generate images based on prompts using the Hugging Face API
+def generate_image(prompt, model_choice, translate=False):
+    if translate:
+        prompt = translate_text(prompt, target_language='en')  # Assuming you want to translate to English
+    model_urls = {
+        "Stable Diffusion v1.5": "https://api-inference.huggingface.co/models/runwayml/stable-diffusion-v1-5",
 
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
+    }
+    API_URL = model_urls[model_choice]
 
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
-        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)
-        
-        result = gr.Image(label="Result", show_label=False)
+    headers = {"Authorization": f"Bearer {os.getenv('API_TOKEN')}"}
+    payload = {"inputs": prompt}
+    data = query(payload, API_URL, headers)
+    try:
+        # Load the image from byte data
+        image = Image.open(BytesIO(data))
+        # Resize the image
+        image = image.resize((400, 400))
+        # Convert the image object back to bytes for Gradio output
+        buf = BytesIO()
+        image.save(buf, format='PNG')
+        buf.seek(0)
+        return image
 
-        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=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
-        )
+    except Exception as e:
+        print("Error processing the image:", e)
+        return None  # Return None or an appropriate error message/image
 
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
-    )
+# Set up environment variable correctly
+API_TOKEN = os.getenv("API_TOKEN")
+
+# Styling with custom CSS
+css = """
+body {background-color: #f0f2f5;}
+.gradio-app {background-color: #ffffff; border-radius: 12px; box-shadow: 0 0 12px rgba(0,0,0,0.1);}
+button {color: white; background-color: #106BA3; border: none; border-radius: 5px;}
+"""
 
-demo.queue().launch()
+# Define interface
+title = "نموذج توليد الصور"
+description = "اكتب وصف للصورة التي تود من النظام التوليدي انشاءها. على سبيل المثال: 'قطة ترتدي قبعة في مشهد شتوي'."
+iface = gr.Interface(
+    fn=generate_image,
+    inputs=[
+        gr.components.Textbox(lines=2, placeholder="Enter the description of the image here..."),
+        gr.components.Dropdown(choices=["Stable Diffusion v1.5",], label="Choose Model", value='Stable Diffusion v1.5'),
+        gr.components.Checkbox(label="Translate The Text Before Generating Image", value=False)
+    ],
+    outputs=gr.components.Image(),
+    title=title,
+    description=description,
+    theme="default",
+    css=css
+)
+# Launch the interface
+iface.launch()