Update app.py

app.py

@@ -6,7 +6,6 @@ import os
 import time
 from PIL import Image
 from deep_translator import GoogleTranslator
-import json
 
 # Project by Nymbo
 
@@ -15,25 +14,39 @@ API_TOKEN = os.getenv("HF_READ_TOKEN")
 headers = {"Authorization": f"Bearer {API_TOKEN}"}
 timeout = 100
 
-# Function to query the API and return the generated image as PNG
-def query(prompt, is_negative=False, steps=35, cfg_scale=7, sampler="DPM++ 2M Karras", seed=-1, strength=0.7, width=1024, height=1024):
-    if prompt == "" or prompt is None:
+def convert_to_png(image):
+    """Convert any image format to true PNG format"""
+    png_buffer = io.BytesIO()
+    if image.mode == 'RGBA':
+        # If image has alpha channel, save as PNG with transparency
+        image.save(png_buffer, format='PNG', optimize=True)
+    else:
+        # Convert to RGB first if not in RGB/RGBA mode
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
+        image.save(png_buffer, format='PNG', optimize=True)
+    png_buffer.seek(0)
+    return Image.open(png_buffer)
+
+def query(prompt, is_negative=False, steps=35, cfg_scale=7, sampler="DPM++ 2M Karras", 
+          seed=-1, strength=0.7, width=1024, height=1024):
+    if not prompt:
         return None
 
     key = random.randint(0, 999)
-    
     API_TOKEN = random.choice([os.getenv("HF_READ_TOKEN")])
     headers = {"Authorization": f"Bearer {API_TOKEN}"}
     
-    # Translate the prompt from Indonesian to English
-    prompt = GoogleTranslator(source='id', target='en').translate(prompt)
-    print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
-
-    # Enhance the prompt
-    prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
+    # Translate prompt
+    try:
+        prompt = GoogleTranslator(source='id', target='en').translate(prompt)
+        print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
+        prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
+    except Exception as e:
+        print(f"Translation error: {e}")
+    
     print(f'\033[1mGeneration {key}:\033[0m {prompt}')
     
-    # Prepare the payload
     payload = {
         "inputs": prompt,
         "is_negative": is_negative,
@@ -41,50 +54,52 @@ def query(prompt, is_negative=False, steps=35, cfg_scale=7, sampler="DPM++ 2M Ka
         "cfg_scale": cfg_scale,
         "seed": seed if seed != -1 else random.randint(1, 1000000000),
         "strength": strength,
-        "parameters": {
-            "width": width,
-            "height": height
-        }
+        "parameters": {"width": width, "height": height}
     }
 
-    # API request
-    response = requests.post(API_URL, headers=headers, json=payload, timeout=timeout)
-    if response.status_code != 200:
-        print(f"Error: Failed to get image. Response status: {response.status_code}")
-        print(f"Response content: {response.text}")
-        if response.status_code == 503:
-            raise gr.Error(f"{response.status_code} : The model is being loaded")
-        raise gr.Error(f"{response.status_code}")
-    
     try:
-        # Convert to PNG
-        image_bytes = response.content
-        img = Image.open(io.BytesIO(image_bytes))
+        response = requests.post(API_URL, headers=headers, json=payload, timeout=timeout)
+        response.raise_for_status()
+        
+        # Convert directly to PNG without intermediate format
+        img = Image.open(io.BytesIO(response.content))
+        png_img = convert_to_png(img)
         
-        # Create PNG in memory
-        png_buffer = io.BytesIO()
-        img.save(png_buffer, format="PNG")
-        png_buffer.seek(0)
-        png_image = Image.open(png_buffer)
+        print(f'\033[1mGeneration {key} completed as PNG!\033[0m')
+        return png_img
         
-        print(f'\033[1mGeneration {key} completed!\033[0m ({prompt})')
-        return png_image
+    except requests.exceptions.RequestException as e:
+        print(f"API Error: {e}")
+        if hasattr(e, 'response') and e.response:
+            if e.response.status_code == 503:
+                raise gr.Error("503: Model is loading, please try again later")
+            raise gr.Error(f"{e.response.status_code}: {e.response.text}")
+        raise gr.Error("Network error occurred")
     except Exception as e:
-        print(f"Error when trying to open the image: {e}")
-        return None
+        print(f"Image processing error: {e}")
+        raise gr.Error(f"Image processing failed: {str(e)}")
 
-# CSS styling
+# Improved CSS
 css = """
 #app-container {
     max-width: 800px;
-    margin-left: auto;
-    margin-right: auto;
+    margin: 0 auto;
+    padding: 20px;
+}
+#prompt-text-input, #negative-prompt-text-input {
+    font-size: 14px;
+}
+#gallery {
+    min-height: 512px;
+    background: #f5f5f5;
+}
+#gen-button {
+    margin: 10px 0;
 }
 """
 
-# Gradio UI
 with gr.Blocks(theme='Nymbo/Nymbo_Theme', css=css) as app:
-    gr.HTML("<center><h1>FLUX.1-Dev</h1></center>")
+    gr.HTML("<center><h1>FLUX.1-Dev (PNG Output)</h1></center>")
     
     with gr.Column(elem_id="app-container"):
         with gr.Row():
@@ -92,44 +107,46 @@ with gr.Blocks(theme='Nymbo/Nymbo_Theme', css=css) as app:
                 with gr.Row():
                     text_prompt = gr.Textbox(
                         label="Prompt", 
-                        placeholder="Enter a prompt here", 
-                        lines=2, 
+                        placeholder="Masukkan prompt dalam Bahasa Indonesia", 
+                        lines=2,
                         elem_id="prompt-text-input"
                     )
                 
-                with gr.Row():
-                    with gr.Accordion("Advanced Settings", open=False):
-                        negative_prompt = gr.Textbox(
-                            label="Negative Prompt", 
-                            placeholder="What should not be in the image", 
-                            value="(deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, misspellings, typos", 
-                            lines=3, 
-                            elem_id="negative-prompt-text-input"
-                        )
-                        with gr.Row():
-                            width = gr.Slider(label="Width", value=1024, minimum=64, maximum=1216, step=32)
-                            height = gr.Slider(label="Height", value=1024, minimum=64, maximum=1216, step=32)
-                        steps = gr.Slider(label="Sampling steps", value=35, minimum=1, maximum=100, step=1)
-                        cfg = gr.Slider(label="CFG Scale", value=7, minimum=1, maximum=20, step=1)
-                        strength = gr.Slider(label="Strength", value=0.7, minimum=0, maximum=1, step=0.001)
-                        seed = gr.Slider(label="Seed", value=-1, minimum=-1, maximum=1000000000, step=1)
-                        method = gr.Radio(
-                            label="Sampling method", 
-                            value="DPM++ 2M Karras", 
-                            choices=["DPM++ 2M Karras", "DPM++ SDE Karras", "Euler", "Euler a", "Heun", "DDIM"]
-                        )
+                with gr.Accordion("Advanced Settings", open=False):
+                    negative_prompt = gr.Textbox(
+                        label="Negative Prompt", 
+                        value="(deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
+                        lines=3
+                    )
+                    with gr.Row():
+                        width = gr.Slider(1024, label="Width", minimum=512, maximum=1536, step=64)
+                        height = gr.Slider(1024, label="Height", minimum=512, maximum=1536, step=64)
+                    with gr.Row():
+                        steps = gr.Slider(35, label="Steps", minimum=10, maximum=100, step=1)
+                        cfg = gr.Slider(7.0, label="CFG Scale", minimum=1.0, maximum=20.0, step=0.5)
+                    with gr.Row():
+                        strength = gr.Slider(0.7, label="Strength", minimum=0.1, maximum=1.0, step=0.01)
+                        seed = gr.Number(-1, label="Seed (-1 for random)")
+                    method = gr.Radio(
+                        ["DPM++ 2M Karras", "DPM++ SDE Karras", "Euler", "Euler a", "Heun", "DDIM"],
+                        value="DPM++ 2M Karras",
+                        label="Sampling Method"
+                    )
 
-        with gr.Row():
-            text_button = gr.Button("Run", variant='primary', elem_id="gen-button")
+        generate_btn = gr.Button("Generate Image", variant="primary")
         
         with gr.Row():
-            image_output = gr.Image(type="pil", label="Image Output", elem_id="gallery")
+            output_image = gr.Image(
+                type="pil",
+                label="Generated PNG Image",
+                format="png",  # Explicitly set output format
+                elem_id="gallery"
+            )
         
-        text_button.click(
-            query, 
-            inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], 
-            outputs=image_output
+        generate_btn.click(
+            fn=query,
+            inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height],
+            outputs=output_image
         )
 
-# Launch the app
-app.launch(show_api=True, share=True)
+app.launch(server_name="0.0.0.0", server_port=7860, share=True)