app.py

#!/usr/bin/env python
import gradio as gr
from PIL import Image
from io import BytesIO
import io
import time
import json
import uuid
import spaces
import base64
import requests
import os
import random
import torch
import subprocess
import numpy as np
import cv2
from transformers import AutoProcessor, AutoModelForCausalLM
from diffusers import DiffusionPipeline
from typing import Tuple
from deep_translator import GoogleTranslator
from datetime import datetime
from mistralai import Mistral
from theme import theme
from fastapi import FastAPI

app = FastAPI()

API_TOKEN = os.getenv("HF_TOKEN")
headers = {"Authorization": f"Bearer {API_TOKEN}"}
timeout = 100

api_key = os.getenv("MISTRAL_API_KEY")
Mistralclient = Mistral(api_key=api_key)

def flip_image(x):
    return np.fliplr(x)

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:  # 添加通用异常处理
        print(f"Error: {e}")
        return "Please upload a photo"

def query(lora_id, prompt, is_negative=False, steps=28, cfg_scale=3.5, sampler="DPM++ 2M Karras", seed=-1, strength=100, width=896, height=1152):
    if prompt == "" or prompt == None:
        return None

    if lora_id.strip() == "" or lora_id == None:
        lora_id = "black-forest-labs/FLUX.1-dev"

    key = random.randint(0, 999)

    API_URL = "https://api-inference.huggingface.co/models/"+ lora_id.strip()

    API_TOKEN = random.choice([os.getenv("HF_TOKEN")])
    headers = {"Authorization": f"Bearer {API_TOKEN}"}
    
    # prompt = GoogleTranslator(source='ru', target='en').translate(prompt)
    # print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
    prompt = GoogleTranslator(source='ru', target='en').translate(prompt)
    print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')

    prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
    print(f'\033[1mGeneration {key}:\033[0m {prompt}')

    # If seed is -1, generate a random seed and use it
    if seed == -1:
        seed = random.randint(1, 1000000000)

    # 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
        }
    }

    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 ({prompt})')
        return image, seed
    except Exception as e:
        print(f"Error when trying to open the image: {e}")
        return None

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"],
]

# 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;
}
""" 

with gr.Blocks(theme=theme, css=css, elem_id="app-container") as app:
    gr.HTML("<center><h1>🎨 Image To Flux Prompt ++ 🇬🇧</h1></center>")
    
    with gr.Tab(label="🖼 Image To Prompt 📄"):
        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.Tab("✍️ Text to Image 🖼"):
        with gr.Column(elem_id="app-container"):
            with gr.Row():
                with gr.Column(elem_id="prompt-container"):
                    with gr.Group():
                        with gr.Row():
                            text_prompt = gr.Textbox(label="Image Prompt ✍️", placeholder="Enter a prompt here", lines=2, show_copy_button = True, elem_id="prompt-text-input")
                                
                        with gr.Row():
                            custom_lora = gr.Dropdown([" ", "prithivMLmods/Canopus-Pencil-Art-LoRA", "prithivMLmods/Flux-Realism-FineDetailed", "prithivMLmods/Fashion-Hut-Modeling-LoRA", "prithivMLmods/SD3.5-Large-Turbo-HyperRealistic-LoRA", "prithivMLmods/Flux-Fine-Detail-LoRA", "prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA", "hugovntr/flux-schnell-realism", "fofr/sdxl-deep-down", "prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0", "prithivMLmods/Canopus-Realism-LoRA", "prithivMLmods/Canopus-LoRA-Flux-FaceRealism", "prithivMLmods/SD3.5-Large-Photorealistic-LoRA", "prithivMLmods/Flux.1-Dev-LoRA-HDR-Realism", "prithivMLmods/Ton618-Epic-Realism-Flux-LoRA", "KappaNeuro/john-singer-sargent-style", "KappaNeuro/alphonse-mucha-style", "ntc-ai/SDXL-LoRA-slider.ultra-realistic-illustration", "ntc-ai/SDXL-LoRA-slider.eye-catching", "KappaNeuro/john-constable-style", "dvyio/flux-lora-film-noir", "dvyio/flux-lora-pro-headshot"], label="Custom LoRA",)
                        
                        with gr.Row():
                            with gr.Accordion("⚙️ Advanced Settings", open=False, elem_id="settings-container"):
                                negative_prompt = gr.Textbox(label="Negative Prompt", lines=5, placeholder="What should not be in the image", value=" (visible hand:1.3), (ugly:1.3), (duplicate:1.2), (morbid:1.1), (mutilated:1.1), out of frame, bad face, extra fingers, mutated hands, (poorly drawn hands:1.1), (poorly drawn face:1.3), (mutation:1.3), (deformed:1.3), blurry, (bad anatomy:1.1), (bad proportions:1.2), (extra limbs:1.1), cloned face, (disfigured:1.2), gross proportions, malformed limbs, (missing arms:1.1), (missing legs:1.1), (extra arms:1.2), (extra legs:1.2), fused fingers, too many fingers, (long neck:1.2), sketched by bad-artist, (bad-image-v2-39000:1.3) ")
                                with gr.Row():
                                    width = gr.Slider(label="Image Width", value=896, minimum=64, maximum=1216, step=32)
                                    height = gr.Slider(label="Image Height", value=1152, minimum=64, maximum=1216, step=32)
                                strength = gr.Slider(label="Prompt Strength", value=100, minimum=0, maximum=100, step=1)    
                                steps = gr.Slider(label="Sampling steps", value=50, minimum=1, maximum=100, step=1)
                                cfg = gr.Slider(label="CFG Scale", value=3.5, minimum=1, maximum=20, step=0.5)
                                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++ 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"])
                        
                        with gr.Row():
                            with gr.Accordion("🫘Seed", open=False):
                                seed_output = gr.Textbox(label="Seed Used", elem_id="seed-output")
                                
            # Add a button to trigger the image generation    
            with gr.Row():
                text_button = gr.Button("Generate Image 🎨", variant='primary', elem_id="gen-button")
                clear_prompt =gr.Button("Clear Prompt 🗑️",variant="primary", elem_id="clear_button")
                clear_prompt.click(lambda: (None), None, [text_prompt], queue=False, show_api=False)

            with gr.Row():
                image_output = gr.Image(type="pil", label="Image Output", format="png", show_share_button=False, elem_id="gallery")
               
            with gr.Row():
                clear_results = gr.Button(value="Clear Image 🗑️", variant="primary", elem_id="clear_button")
                clear_results.click(lambda: (None), None, [image_output], queue=False, show_api=False)
            
            with gr.Row():
                gr.Examples(
                    examples = examples,
                    inputs = [text_prompt],
            )

                    
            text_button.click(query, inputs=[custom_lora, text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], outputs=[image_output, seed_output])
    
    with gr.Tab("📝 Lora trigger words|"):
        with gr.Row():            
            with gr.Column():
                    gr.Markdown(
                """
                <div class="cell right">
                <div style="max-width: 650px; margin: 2rem auto; padding: 1rem; border-radius: 10px; background-color: #f0f0f0; float: right;">
                    <h2 style="font-size: 1.5rem; margin-bottom: 1rem;">Lora trigger words</h2>
                    <ol style="padding-left: 1.5rem;">
                        <li>Canopus-Pencil-Art-LoRA**: Pencil Art</li>
                        <li>Flux-Realism-FineDetailed**: Fine Detailed</li>
                        <li>Fashion-Hut-Modeling-LoRA**: Modeling</li>
                        <li>SD3.5-Large-Turbo-HyperRealistic-LoRA**: hyper realistic</li>
                        <li>Flux-Fine-Detail-LoRA**: Super Detail</li>
                        <li>SD3.5-Turbo-Realism-2.0-LoRA**: Turbo Realism</li>
                        <li>Canopus-LoRA-Flux-UltraRealism-2.0**: Ultra realistic</li> 
                        <li>Canopus-Pencil-Art-LoRA**: Pencil Art</li>
                        <li>SD3.5-Large-Photorealistic-LoRA**: photorealistic</li>
                        <li>Flux.1-Dev-LoRA-HDR-Realism**: HDR</li>
                        <li>prithivMLmods/Ton618-Epic-Realism-Flux-LoRA**: Epic Realism</li>
                        <li>john-singer-sargent-style**: John Singer Sargent Style</li>
                        <li>alphonse-mucha-style**: Alphonse Mucha Style</li>
                        <li>ultra-realistic-illustration**: ultra realistic illustration</li>
                        <li>eye-catching**: eye-catching</li>
                        <li>john-constable-style**: John Constable Style</li>
                        <li>film-noir**: in the style of FLMNR</li>
                        <li>flux-lora-pro-headshot**: PROHEADSHOT</li>
                   </ol>     
                </div>
                """
                )
        
    with gr.Tab("🔄 Flip Image", visible=False):
        with gr.Row():
            image_input = gr.Image(label="Upload Image", height=320, type="filepath")
            image_output = gr.Image(format="png")
        with gr.Row():    
            image_button = gr.Button("Run", variant='primary')
            image_button.click(flip_image, inputs=image_input, outputs=image_output)
        with gr.Row():     
            clear_results = gr.Button(value="Clear Image", variant="primary", elem_id="clear_button")
            clear_results.click(lambda: (None, None), None, [image_input, image_output]) 

    with gr.Tab("ℹ️ Tips"):
        with gr.Row():
            with gr.Column():
                gr.Markdown(
        """
        <div style="max-width: 650px; margin: 2rem auto; padding: 1rem; border-radius: 10px; background-color: #f0f0f0;">
            <h2 style="float: left; font-size: 1.5rem; margin-bottom: 1rem;">How to Use</h2>
            <ol style="padding-left: 1.5rem;">
                <li>Add an image to generate a prompt, this is optional.</li>
                <li>If using an image to prompt, copy the prompt and paste into the prompt on tab 2</li>
                <li>Enter a detailed description of the image you want to create.</li>
                <li>Adjust advanced settings if desired (tap to expand).</li>
                <li>Tap "Generate Image" and wait for your creation!</li>
            </ol>
            <p style="margin-top: 1rem; font-style: italic;">Tip: Be specific in your description for best results!</p>
            <p style="margin-top: 1rem; font-style: italic;">*Note: Some LoRA models will not work every time (not sure why), refresh the page and try again</p>
            <p style="margin-top: 1rem; font-style: italic;">*I'm still playing around to try to sort the issue, feel free to let me know if you find a fix</p>
        </div>
        """
        )
        
if __name__ == "__main__":
    app.launch()