import gradio as gr import requests import io import random import os from PIL import Image from deep_translator import GoogleTranslator from gradio_client import Client # Import the gradio client for prompt enhancement # os.makedirs('assets', exist_ok=True) if not os.path.exists('icon.jpg'): os.system("wget -O icon.jpg https://i.pinimg.com/564x/64/49/88/644988c59447eb00286834c2e70fdd6b.jpg") 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 # Function to set the system prompt once def set_system_prompt(): client = Client("Qwen/Qwen2.5-72B-Instruct") result = client.predict( system="You are Qwen, an image generation prompt enhancer", api_name="/modify_system_session" ) print(f"System session modified: {result}") return result # Function to enhance the prompt with Qwen model def enhance_prompt_with_qwen(prompt): client = Client("Qwen/Qwen2.5-72B-Instruct") result = client.predict( query=prompt, history=[], system="You are Qwen, an image generation prompt enhancer", api_name="/model_chat" ) # Extract the relevant part of the tuple, index [0], which contains the enhanced prompt. enhanced_prompt = result[0] # This is the string we need for the image generation prompt. print(f"Enhanced prompt: {enhanced_prompt}") return enhanced_prompt # Image generation query function 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): # Set system prompt first set_system_prompt() # Enhance the prompt before translation enhanced_prompt = enhance_prompt_with_qwen(prompt) # 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") headers = {"Authorization": f"Bearer {API_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.") headers = {"Authorization": f"Bearer {huggingface_api_key}"} if enhanced_prompt == "" or enhanced_prompt is None: return None key = random.randint(0, 999) # Translate the enhanced prompt enhanced_prompt = GoogleTranslator(source='ru', target='en').translate(enhanced_prompt) print(f'\033[1mGeneration {key} translation:\033[0m {enhanced_prompt}') enhanced_prompt = f"{enhanced_prompt} | ultra detail, ultra elaboration, ultra quality, perfect." print(f'\033[1mGeneration {key}:\033[0m {enhanced_prompt}') # If seed is -1, generate a random seed and use it if seed == -1: seed = random.randint(1, 1000000000) payload = { "inputs": enhanced_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 ({enhanced_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 except Exception as e: print(f"Error when trying to open the image: {e}") return None, None css = """ #app-container { max-width: 600px; margin-left: auto; margin-right: auto; } #title-container { display: flex; align-items: center; justify-content: center; } #title-icon { width: 32px; /* Adjust the width of the icon as needed */ height: auto; margin-right: 10px; /* Space between icon and title */ } #title-text { font-size: 24px; /* Adjust font size as needed */ font-weight: bold; } """ with gr.Blocks(theme='Nymbo/Nymbo_Theme', css=css) as app: gr.HTML("""
Icon

FLUX Capacitor

""") 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") 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") seed_output = gr.Textbox(label="Seed Used", elem_id="seed-output") # Adjust the click function to include the API key and use_dev as inputs text_button.click(query, inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, huggingface_api_key, use_dev], outputs=[image_output, seed_output]) app.launch(show_api=True, share=False)