app.py

# Imports
import gradio as gr
import threading
import requests
import random
import spaces
import torch
import uuid
import json
import os

from diffusers import StableDiffusionXLPipeline, StableDiffusion3Pipeline, SD3Transformer2DModel, FlashFlowMatchEulerDiscreteScheduler
from huggingface_hub import snapshot_download
from peft import PeftModel
from PIL import Image

# Pre-Initialize
DEVICE = "auto"
if DEVICE == "auto":
    DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
print(f"[SYSTEM] | Using {DEVICE} type compute device.")

# Variables
HF_TOKEN = os.environ.get("HF_TOKEN")

MAX_SEED = 9007199254740991
DEFAULT_INPUT = ""
DEFAULT_NEGATIVE_INPUT = "(bad, ugly, amputation, abstract, blur, deformed, distorted, disfigured, disconnected, mutation, mutated, low quality, lowres), unfinished, text, signature, watermark, (limbs, legs, feet, arms, hands), (porn, nude, naked, nsfw)"
DEFAULT_MODEL = "Default"
DEFAULT_HEIGHT = 1024
DEFAULT_WIDTH = 1024

headers = {"Content-Type": "application/json", "Authorization": f"Bearer {HF_TOKEN}" }

css = '''
.gradio-container{max-width: 560px !important}
h1{text-align:center}
footer {
    visibility: hidden
}
'''

repo_default = StableDiffusionXLPipeline.from_pretrained("fluently/Fluently-XL-Final", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False)
repo_default.load_lora_weights("ehristoforu/dalle-3-xl-v2", adapter_name="base")
repo_default.set_adapters(["base"], adapter_weights=[0.7])

repo_pixel = StableDiffusionXLPipeline.from_pretrained("fluently/Fluently-XL-Final", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False)
repo_pixel.load_lora_weights("artificialguybr/PixelArtRedmond", adapter_name="base")
repo_pixel.load_lora_weights("nerijs/pixel-art-xl", adapter_name="base2")
repo_pixel.set_adapters(["base", "base2"], adapter_weights=[1, 1])

repo_large_path = snapshot_download(repo_id="stabilityai/stable-diffusion-3-medium", revision="refs/pr/26", token=HF_TOKEN)
repo_large_transformer_path = SD3Transformer2DModel.from_pretrained(repo_large_path, subfolder="transformer", torch_dtype=torch.float16)
repo_large_transformer = PeftModel.from_pretrained(repo_large_transformer_path, "jasperai/flash-sd3")

repo_customs = {
    "Default": repo_default,
    "Realistic": StableDiffusionXLPipeline.from_pretrained("ehristoforu/Visionix-alpha", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False),
    "Anime": StableDiffusionXLPipeline.from_pretrained("cagliostrolab/animagine-xl-3.1", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False),
    "Pixel": repo_pixel,
    "Large": StableDiffusion3Pipeline.from_pretrained(repo_large_path, transformer=repo_large_transformer, torch_dtype=torch.float16, use_safetensors=True),
}

repo_customs["Large"].scheduler = FlashFlowMatchEulerDiscreteScheduler.from_pretrained(repo_large_path, subfolder="scheduler")

# Functions
def save_image(img, seed):
    name = f"{seed}-{uuid.uuid4()}.png"
    img.save(name)
    return name
    
def get_seed(seed):
    seed = seed.strip()
    if seed.isdigit():
        return int(seed)
    else:
        return random.randint(0, MAX_SEED)

def api_classification_request(url, filename, headers):
    with open(filename, "rb") as file:
        data = file.read()
    response = requests.request("POST", url, headers=headers or {}, data=data)
    return json.loads(response.content.decode("utf-8"))

@spaces.GPU(duration=60)
def generate(input=DEFAULT_INPUT, filter_input="", negative_input=DEFAULT_NEGATIVE_INPUT, model=DEFAULT_MODEL, height=DEFAULT_HEIGHT, width=DEFAULT_WIDTH, steps=1, guidance=0, number=1, seed=None):

    threading.Thread(target=api_classification_request, args=("https://api-inference.huggingface.co/models/Falconsai/nsfw_image_detection", "./Image.png", headers))

    repo = repo_customs[model or "Default"]
    filter_input = filter_input or ""
    negative_input = negative_input or DEFAULT_NEGATIVE_INPUT
    steps_set = steps
    guidance_set = guidance
    seed = get_seed(seed)

    print(input, filter_input, negative_input, model, height, width, steps, guidance, number, seed)
    
    if model == "Realistic":   
        steps_set = 25
        guidance_set = 7
    elif model == "Anime":   
        steps_set = 25
        guidance_set = 7
    elif model == "Pixel":   
        steps_set = 15
        guidance_set = 1.5
    elif model == "Large":   
        steps_set = 15
        guidance_set = 1.5
    else:
        steps_set = 25
        guidance_set = 7

    if not steps:
        steps = steps_set
    if not guidance:
        guidance = guidance_set
    
    print(steps, guidance)

    repo.to(DEVICE)
    
    parameters = {
        "prompt": input,
        "negative_prompt": filter_input + negative_input,
        "height": height,
        "width": width,
        "num_inference_steps": steps,
        "guidance_scale": guidance,
        "num_images_per_prompt": number,
        "generator": torch.Generator().manual_seed(seed),
        "output_type":"pil",
    }
    
    images = repo(**parameters).images
    image_paths = [save_image(img, seed) for img in images]

    print(image_paths)
    
    nsfw_prediction = api_classification_request("https://api-inference.huggingface.co/models/Falconsai/nsfw_image_detection", image_paths[0], headers)

    print(nsfw_prediction)

    return image_paths, {item['label']: round(item['score'], 3) for item in nsfw_prediction}

def cloud():
    print("[CLOUD] | Space maintained.")

# Initialize
with gr.Blocks(css=css) as main:
    with gr.Column():
        gr.Markdown("🪄 Generate high quality images in all styles.")
        
    with gr.Column():
        input = gr.Textbox(lines=1, value=DEFAULT_INPUT, label="Input")
        filter_input = gr.Textbox(lines=1, value="", label="Input Filter")
        negative_input = gr.Textbox(lines=1, value=DEFAULT_NEGATIVE_INPUT, label="Input Negative")
        model = gr.Dropdown(choices=repo_customs.keys(), value="Default", label="Model")
        height = gr.Slider(minimum=8, maximum=2160, step=1, value=DEFAULT_HEIGHT, label="Height")
        width = gr.Slider(minimum=8, maximum=2160, step=1, value=DEFAULT_WIDTH, label="Width")
        steps = gr.Slider(minimum=1, maximum=100, step=1, value=25, label="Steps")
        guidance = gr.Slider(minimum=0, maximum=100, step=0.1, value=5, label = "Guidance")
        number = gr.Slider(minimum=1, maximum=4, step=1, value=1, label="Number")
        seed = gr.Textbox(lines=1, value="", label="Seed (Blank for random)")
        submit = gr.Button("▶")
        maintain = gr.Button("☁️")

    with gr.Column():
        output = gr.Gallery(columns=1, label="Image")
        output_2 = gr.Label()
            
    submit.click(generate, inputs=[input, filter_input, negative_input, model, height, width, steps, guidance, number, seed], outputs=[output, output_2], queue=False)
    maintain.click(cloud, inputs=[], outputs=[], queue=False)

main.launch(show_api=True)