import gradio as gr import requests import io import random import os from PIL import Image from huggingface_hub import InferenceClient from deep_translator import GoogleTranslator from gradio_client import Client # os.makedirs('assets', exist_ok=True) if not os.path.exists('icon.png'): os.system("wget -O icon.png 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 def enhance_prompt(prompt, style="photorealistic"): client = Client("K00B404/Mistral-Nemo-custom") result = client.predict( system_prompt="You are a image generation prompt enhancer and must respond only with the enhanced version of the users input prompt", user_message=f"###input image generation prompt### {prompt}", 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_option=False): # 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 = 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(prompt) print(f'\033[1mGeneration {key} enhanced prompt:\033[0m {prompt}') if use_mistral_nemo: prompt = mistral_nemo_call(prompt,API_TOKEN=API_TOKEN, model='meta-llama/Llama-3.2-1B',style="cartoon") 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 css = """ body { background-image: url('icon.png'); background-size: cover; background-repeat: no-repeat; background-attachment: fixed; } #app-container { background-color: rgba(255, 255, 255, 0.8); /* semi-transparent white */ max-width: 600px; margin-left: auto; margin-right: auto; padding: 20px; border-radius: 10px; box-shadow: 0 0 10px rgba(0,0,0,0.1); } #title-container { display: flex; align-items: center; justify-content: center; } #title-icon { width: 32px; height: auto; margin-right: 10px; } #title-text { font-size: 24px; font-weight: bold; } """ css1 = """ #app-container { max-width: 600px; margin-left: auto; margin-right: auto; } #title-container { display: flex; align-items: center; justify-content: center; } #app-container { max-width: 600px; margin-left: auto; margin-right: auto; background-color: rgba(255, 255, 255, 0.001); /* semi-transparent white */ padding: 20px; border-radius: 10px; } #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("""