import gradio as gr import requests import io import random import os import time from PIL import Image from mistralai import Mistral from deep_translator import GoogleTranslator import json from theme import theme from fastapi import FastAPI app = FastAPI() # Based on a project by Nymbo API_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-dev" 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 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: 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 Russian to English if necessary prompt = GoogleTranslator(source='ru', target='en').translate(prompt) print(f'\033[1mGeneration {key} translation:\033[0m {prompt}') # Add some extra flair to the prompt prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect." print(f'\033[1mGeneration {key}:\033[0m {prompt}') # Prepare the payload for the API call, including width and height payload = { "inputs": prompt, "is_negative": is_negative, "steps": steps, "cfg_scale": cfg_scale, "seed": seed if seed != -1 else random.randint(1, 1000000000), "strength": strength, "parameters": { "width": width, # Pass the width to the API "height": height # Pass the height to the API } } # Send the request to the API and handle the response 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 the response content into an image image_bytes = response.content image = Image.open(io.BytesIO(image_bytes)) print(f'\033[1mGeneration {key} completed!\033[0m ({prompt})') return image except Exception as e: print(f"Error when trying to open the image: {e}") return None def encode_image(image_path): """Encode the image to base64.""" try: # Open the image file image = Image.open(image_path).convert("RGB") # Resize the image to a height of 512 while maintaining the aspect ratio base_height = 512 h_percent = (base_height / float(image.size[1])) w_size = int((float(image.size[0]) * float(h_percent))) image = image.resize((w_size, base_height), Image.LANCZOS) # Convert the image to a byte stream buffered = BytesIO() image.save(buffered, format="JPEG") img_str = base64.b64encode(buffered.getvalue()).decode("utf-8") return img_str except FileNotFoundError: print(f"Error: The file {image_path} was not found.") return None except Exception as e: # Add generic exception handling print(f"Error: {e}") return None def feifeichat(image): try: model = "pixtral-large-2411" # Define the messages for the chat base64_image = encode_image(image) messages = [{ "role": "user", "content": [ { "type": "text", "text": "Please provide a detailed description of this photo" }, { "type": "image_url", "image_url": f"data:image/jpeg;base64,{base64_image}" }, ], "stream": False, }] partial_message = "" for chunk in Mistralclient.chat.stream(model=model, messages=messages): if chunk.data.choices[0].delta.content is not None: partial_message = partial_message + chunk.data.choices[ 0].delta.content yield partial_message except Exception as e: # Adding generic exception handling print(f"Error: {e}") return "Please upload a photo" # CSS to style the app css = """ .gradio-container {background-color: MediumAquaMarine} footer{display:none !important} #app-container { max-width: 930px; margin-left: auto; margin-right: auto; } """ examples = [ "a beautiful woman with blonde hair and blue eyes", "a beautiful woman with brown hair and grey eyes", "a beautiful woman with black hair and brown eyes", ] # Build the Gradio UI with Blocks with gr.Blocks(theme=theme, css=css) as app: # Add a title to the app gr.HTML("

FLUX.1-Dev

") with gr.Tabs() as tabs: with gr.TabItem(label="🖼 Image To Prompt 📄", visible=True): with gr.Row(): with gr.Column(): input_img = gr.Image(label="Input Picture 🖼️",height=320,type="filepath") submit_btn = gr.Button(value="Submit", variant='primary') with gr.Column(): output_text = gr.Textbox(label="Flux Prompt ✍️", show_copy_button = True) clr_button =gr.Button("Clear 🗑️ ",variant="primary", elem_id="clear_button") clr_button.click(lambda: (None, None), None, [input_img, output_text], queue=False, show_api=False) submit_btn.click(feifeichat, [input_img], [output_text]) with gr.TabItem("✍️ Text to Image 🖼", visible=True): # Container for all the UI elements with gr.Column(elem_id="app-container"): # Add a text input for the main prompt 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") # Accordion for advanced settings 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) # Setting the seed to -1 will make it random method = gr.Radio(label="Sampling method", value="DPM++ 2M Karras", choices=["DPM++ 2M Karras", "DPM++ 2S a Karras", "DPM2 a Karras", "DPM2 Karras", "DPM++ SDE Karras", "DEIS", "LMS", "DPM Adaptive", "DPM++ 2M", "DPM2 Ancestral", "DPM++ S", "DPM++ SDE", "DDPM", "DPM Fast", "dpmpp_2s_ancestral", "Euler", "Euler CFG PP", "Euler a", "Euler Ancestral", "Euler+beta", "Heun", "Heun PP2", "DDIM", "LMS Karras", "PLMS", "UniPC", "UniPC BH2"]) # Add a button to trigger the image generation with gr.Row(): text_button = gr.Button("Run", variant='primary', elem_id="gen-button") # Image output area to display the generated image with gr.Row(): image_output = gr.Image(type="pil", label="Image Output", show_share_button=False, elem_id="gallery") with gr.Row(): clear_prompt =gr.Button("Clear 🗑️",variant="primary", elem_id="clear_button") clear_prompt.click(lambda: (None, None), None, [text_prompt, image_output], queue=False, show_api=False) with gr.Row(): gr.Examples( examples = examples, inputs = [text_prompt], ) # Bind the button to the query function with the added width and height inputs text_button.click(query, inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], outputs=image_output) app.queue(default_concurrency_limit=200, max_size=200) # <-- Sets up a queue with default parameters if __name__ == "__main__": # Launch the Gradio app app.launch(show_api=False, share=True)