Update app.py

app.py

@@ -1,45 +1,346 @@
+
 import gradio as gr
+import requests
+import io
+import random
+import os
+from PIL import Image
+from huggingface_hub import InferenceClient
+from gradio_client import Client
+import logging
+from datetime import datetime
+
+import sqlite3
+from datetime import datetime
+
+
+# Initialize the database
+def init_db(file='logs.db'):
+    conn = sqlite3.connect(file)
+    c = conn.cursor()
+    c.execute('''CREATE TABLE IF NOT EXISTS logs
+                 (timestamp TEXT, message TEXT)''')
+    conn.commit()
+    conn.close()
+
+# Log a request
+def log_request(prompt, is_negative, steps, cfg_scale, sampler, seed, strength, use_dev, enhance_prompt_style, enhance_prompt_option, nemo_enhance_prompt_style, use_mistral_nemo, huggingface_api_key):
+    log_message = f"Request: prompt='{prompt}', is_negative={is_negative}, steps={steps}, cfg_scale={cfg_scale}, "
+    log_message += f"sampler='{sampler}', seed={seed}, strength={strength}, use_dev={use_dev}, "
+    log_message += f"enhance_prompt_style='{enhance_prompt_style}', enhance_prompt_option={enhance_prompt_option}, "
+    log_message += f"nemo_enhance_prompt_style='{nemo_enhance_prompt_style}', use_mistral_nemo={use_mistral_nemo}"
+    if huggingface_api_key:
+        log_message += f"huggingface_api_key='{huggingface_api_key}'"
+    
+    conn = sqlite3.connect('acces_log.log')
+    c = conn.cursor()
+    c.execute("INSERT INTO logs VALUES (?, ?)", (datetime.now().isoformat(), log_message))
+    conn.commit()
+    conn.close()
+    
+# os.makedirs('assets', exist_ok=True)
+if not os.path.exists('icon.png'):
+    os.system("wget -O icon.png https://huggingface.co/spaces/K00B404/FLUX.1-Dev-Serverless-darn-enhanced-prompt/resolve/main/edge.png")
+API_URL_DEV = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-dev"
+API_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-schnell"
+timeout = 100
+init_db('acces_log.log')
+client = Client("https://https://huggingface.co/spaces/K00B404/SnelleJelle")
+# Set up logging
+logging.basicConfig(filename='access.log', level=logging.INFO,
+                    format='%(asctime)s - %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+
+
+
+def log_requestold(prompt, is_negative, steps, cfg_scale, sampler, seed, strength, use_dev, enhance_prompt_style, enhance_prompt_option, nemo_enhance_prompt_style, use_mistral_nemo, huggingface_api_key):
+    log_message = f"Request: prompt='{prompt}', is_negative={is_negative}, steps={steps}, cfg_scale={cfg_scale}, "
+    log_message += f"sampler='{sampler}', seed={seed}, strength={strength}, use_dev={use_dev}, "
+    log_message += f"enhance_prompt_style='{enhance_prompt_style}', enhance_prompt_option={enhance_prompt_option}, "
+    log_message += f"nemo_enhance_prompt_style='{nemo_enhance_prompt_style}', use_mistral_nemo={use_mistral_nemo}"
+    if huggingface_api_key:
+        log_message += f"huggingface_api_key='{huggingface_api_key}'"
+    logging.info(log_message)
+
+
+def check_ubuse(prompt,word_list=["little girl"]):
+    for word in word_list:
+        if word in prompt:
+            print(f"Abuse! prompt {prompt} wiped!")
+            return "None"
+    return prompt
+
+
+def enhance_prompt(prompt, style="photo-realistic"):
+    system_message = f"""
+    You are an image generation prompt enhancer specialized in the {style} style. 
+    You must respond only with the enhanced version of the user's input prompt.
+    Remember, image generation models can be stimulated by referring to camera 'effects' in the prompt like: 4k, award-winning, super details, 35mm lens, hd
+    """
+    
+    result = client.predict(
+        message=prompt,
+        system_message=system_message,
+        max_tokens=512,
+        temperature=0.7,
+        top_p=0.95,
+        api_name="/chat"
+    )
+    return result
+
+
+
+def enhance_prompt(prompt, model="mistralai/Mistral-Nemo-Instruct-2407", style="photo-realistic"):
+    system_prompt=f"""
+    You are a image generation prompt enhancer specialized in the {style} style. 
+    You must respond only with the enhanced version of the users input prompt
+    Remember, image generation models can be stimulated by refering to camera 'effect' in the prompt like :4k ,award winning, super details, 35mm lens, hd
+    """
+
+    result = client.predict(
+    		system_prompt=system_prompt,
+    		user_message=user_message,
+    		max_tokens=256,
+    		model_id=model,# "mistralai/Mistral-Nemo-Instruct-2407",
+    		api_name="/chat"
+    )
+    return result
+    
+    # The output value that appears in the "Response" Textbox component.
+    """result = client.predict(
+        system_prompt=system_prompt,#"You are a image generation prompt enhancer and must respond only with the enhanced version of the users input prompt",
+        user_message=user_message,
+        max_tokens=500,
+        api_name="/predict"
+    )
+    return result
+    """
+
+
+def enhance_prompt_v2(prompt, model="mistralai/Mistral-Nemo-Instruct-2407", style="photo-realistic"):
+    
+    client = Client("K00B404/Mistral-Nemo-custom")
+    
+    system_prompt=f"""
+    You are a image generation prompt enhancer specialized in the {style} style. 
+    You must respond only with the enhanced version of the users input prompt
+    Remember, image generation models can be stimulated by refering to camera 'effect' in the prompt like :4k ,award winning, super details, 35mm lens, hd
+    """
+    user_message=f"###input image generation prompt### {prompt}"
+   
+    result = client.predict(
+    		system_prompt=system_prompt,
+    		user_message=user_message,
+    		max_tokens=256,
+    		model_id=model,
+    		api_name="/predict"
+    )
+    return result
+
+    
+def mistral_nemo_call(prompt, API_TOKEN, model="mistralai/Mistral-Nemo-Instruct-2407", style="photo-realistic"):
+    
+    client = InferenceClient(api_key=API_TOKEN)
+    system_prompt=f"""
+    You are a image generation prompt enhancer specialized in the {style} style. 
+    You must respond only with the enhanced version of the users input prompt
+    Remember, image generation models can be stimulated by refering to camera 'effect' in the prompt like :4k ,award winning, super details, 35mm lens, hd
+    """
+    
+    response = ""
+    for message in client.chat_completion(
+        model=model,
+        messages=[{"role": "system", "content": system_prompt},
+                  {"role": "user", "content": prompt}
+                 ],
+        max_tokens=500,
+        stream=True,
+    ):
+        response += message.choices[0].delta.content
+    return response
+    
+def query(prompt, is_negative=False, steps=30, cfg_scale=7, sampler="DPM++ 2M Karras", seed=-1, strength=0.7, huggingface_api_key=None, use_dev=False,enhance_prompt_style="generic", enhance_prompt_option=False, nemo_enhance_prompt_style="generic", use_mistral_nemo=False):
+    
+    log_request(prompt, is_negative, steps, cfg_scale, sampler, seed, strength, use_dev, enhance_prompt_style, enhance_prompt_option, nemo_enhance_prompt_style, use_mistral_nemo, huggingface_api_key)
+    # Determine which API URL to use
+    api_url = API_URL_DEV if use_dev else API_URL
+
+    # Check if the request is an API call by checking for the presence of the huggingface_api_key
+    is_api_call = huggingface_api_key is not None
+
+    if is_api_call:
+        # Use the environment variable for the API key in GUI mode
+        API_TOKEN = os.getenv("HF_READ_TOKEN")
+    else:
+        # Validate the API key if it's an API call
+        if huggingface_api_key == "":
+            raise gr.Error("API key is required for API calls.")
+        API_TOKEN = huggingface_api_key
+    
+    headers = {"Authorization": f"Bearer {API_TOKEN}"} 
+
+    if prompt == "" or prompt is None:
+        return None, None, None
+
+    key = random.randint(0, 999)
+    prompt = check_ubuse(prompt)
+    #prompt = GoogleTranslator(source='ru', target='en').translate(prompt)
+    print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
+
+    original_prompt = prompt
+    if enhance_prompt_option:
+        prompt = enhance_prompt_v2(prompt, style=enhance_prompt_style)
+        print(f'\033[1mGeneration {key} enhanced prompt:\033[0m {prompt}')
+    if use_mistral_nemo:
+        prompt = mistral_nemo_call(prompt, API_TOKEN=API_TOKEN, style=nemo_enhance_prompt_style)
+        print(f'\033[1mGeneration {key} Mistral-Nemo prompt:\033[0m {prompt}')
+        
+    final_prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
+    print(f'\033[1mGeneration {key}:\033[0m {final_prompt}')
+
+    # If seed is -1, generate a random seed and use it
+    if seed == -1:
+        seed = random.randint(1, 1000000000)
+
+    payload = {
+        "inputs": final_prompt,
+        "is_negative": is_negative,
+        "steps": steps,
+        "cfg_scale": cfg_scale,
+        "seed": seed,
+        "strength": strength
+    }
+
+    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:
+        image_bytes = response.content
+        image = Image.open(io.BytesIO(image_bytes))
+        print(f'\033[1mGeneration {key} completed!\033[0m ({final_prompt})')
+
+        # Save the image to a file and return the file path and seed
+        output_path = f"./output_{key}.png"
+        image.save(output_path)
+        
+        return output_path, seed, prompt if enhance_prompt_option else original_prompt
+    except Exception as e:
+        print(f"Error when trying to open the image: {e}")
+        return None, None, None
+
+
+  
+title_html="""
+    <center>
+        <div id="title-container">
+            <h1 id="title-text">FLUX Capacitor</h1>
+        </div>
+    </center>
+"""
 
-# Custom CSS for the glowing effect
 css = """
-<style>
-  .glowing-panel {
-    position: absolute;
-    top: calc(50% - 150px);
-    left: calc(50% - 150px);
-    width: 300px;
-    height: 300px;
-    border-radius: 50%;
-    box-shadow:
-      inset 0 0 50px #fff,
-      inset 20px 0 80px #f0f,
-      inset -20px 0 80px #0ff,
-      inset 20px 0 300px #f0f,
-      inset -20px 0 300px #0ff,
-      0 0 50px #fff,
-      -10px 0 80px #f0f,
-      10px 0 80px #0ff;
-  }
-</style>
+.gradio-container {
+    background: url(https://huggingface.co/spaces/K00B404/FLUX.1-Dev-Serverless-darn-enhanced-prompt/resolve/main/edge.png);
+    background-size: 900px 880px;
+    background-repeat: no-repeat;
+    background-position: center;
+    background-attachment: fixed;
+    color:#000;
+}
+.dark\:bg-gray-950:is(.dark *) {
+  --tw-bg-opacity: 1;
+  background-color: rgb(157, 17, 142);
+}
+.gradio-container-4-41-0 .prose :last-child {
+  margin-top: 8px !important;
+}
+.gradio-container-4-41-0 .prose :last-child {
+  margin-bottom: -7px !important;
+}
+.dark {
+    --button-primary-background-fill: #09e60d70;
+    --button-primary-background-fill-hover: #00000070;
+    --background-fill-primary: #000;
+    --background-fill-secondary: #000;
+}
+.hide-container {
+    margin-top;-2px;
+}
+#app-container3 {
+    background-color: rgba(255, 255, 255, 0.001);  /* Corrected to make semi-transparent */
+    max-width: 600px;
+    margin-left: auto;
+    margin-right: auto;
+    margin-bottom: 10px;
+    border-radius: 125px;
+    box-shadow: 0 0 10px rgba(0,0,0,0.1); /* Adjusted shadow opacity */
+}
+#app-container {
+    background-color: rgba(255, 255, 255, 0.001);  /* Semi-transparent background */
+    max-width: 600px;
+    margin: 0 auto;  /* Center horizontally */
+    padding-bottom: 10px;
+    border-radius: 25px;
+    box-shadow: 0 0 10px rgba(0, 0, 0, 0.1); /* Adjusted shadow opacity */
+}
+#title-container {
+    display: flex;
+    align-items: center
+    margin-bottom:10px;
+    justify-content: center;
+}
+#title-icon {
+    width: 32px;
+    height: auto;
+    margin-right: 10px;
+}
+#title-text {
+    font-size: 30px;
+    font-weight: bold;
+    color: #000;
+}
 """
 
-def demo_function(input_text):
-    return f"You entered: {input_text}"
-
-# Create a Gradio interface
-with gr.Blocks() as demo:
-    gr.HTML(css)  # Add custom CSS
-    with gr.Row():
-        with gr.Column():
-            gr.Markdown("## Welcome to the Glowing Panel App")
-            input_text = gr.Textbox(label="Enter something:")
-            output_text = gr.Textbox(label="Output:", interactive=False)
-            submit_button = gr.Button("Submit")
-            
-            submit_button.click(demo_function, inputs=input_text, outputs=output_text)
-
-        # Create the glowing panel
-        gr.HTML('<div class="glowing-panel"></div>')
-
-# Launch the app
-demo.launch()
+
+with gr.Blocks(theme='Nymbo/Nymbo_Theme', css=css) as app:
+
+
+    
+    gr.HTML(title_html) # title html 
+    
+    with gr.Column(elem_id="app-container"):
+        with gr.Row():
+            with gr.Column(elem_id="prompt-container"):
+                with gr.Row():
+                    text_prompt = gr.Textbox(label="Prompt", placeholder="Enter a prompt here", 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")
+                        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)
+                        method = gr.Radio(label="Sampling method", value="DPM++ 2M Karras", choices=["DPM++ 2M Karras", "DPM++ SDE Karras", "Euler", "Euler a", "Heun", "DDIM"])
+                        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)
+                        huggingface_api_key = gr.Textbox(label="Hugging Face API Key (required for API calls)", placeholder="Enter your Hugging Face API Key here", type="password", elem_id="api-key")
+                        use_dev = gr.Checkbox(label="Use Dev API", value=False, elem_id="use-dev-checkbox")
+                        enhance_prompt_style =  gr.Textbox(label="Enhance Prompt Style", placeholder="Enter style for the prompt enhancer here", elem_id="enhance-prompt-style")
+                        enhance_prompt_option = gr.Checkbox(label="Enhance Prompt", value=False, elem_id="enhance-prompt-checkbox")
+                        use_mistral_nemo = gr.Checkbox(label="Use Mistral Nemo", value=False, elem_id="use-mistral-checkbox")
+                        nemo_prompt_style =  gr.Textbox(label="Nemo Enhance Prompt Style", placeholder="Enter style for the prompt enhancer here", elem_id="nemo-enhance-prompt-style")
+                        
+        with gr.Row():
+            text_button = gr.Button("Run", variant='primary', elem_id="gen-button")
+        with gr.Row():
+            image_output = gr.Image(type="pil", label="Image Output", elem_id="gallery")
+        with gr.Row():
+            seed_output = gr.Textbox(label="Seed Used", elem_id="seed-output")
+            final_prompt_output = gr.Textbox(label="Final Prompt", elem_id="final-prompt-output")
+        
+        # Adjust the click function to include the API key, use_dev, and enhance_prompt_option as inputs
+        text_button.click(query, inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, huggingface_api_key, use_dev, enhance_prompt_style,enhance_prompt_option, enhance_prompt_style, use_mistral_nemo], outputs=[image_output, seed_output, final_prompt_output])
+
+app.launch(show_api=True, share=False)