app.py

import os
import random
import uuid

import numpy as np
from PIL import Image
import spaces
import torch
from diffusers import DiffusionPipeline


from flask import Flask, flash, request
from flask_session import Session


app = Flask(__name__)
app.config["SESSION_PERMANENT"] = False
app.config["SESSION_TYPE"] = "filesystem"

Session(app)


DESCRIPTION = """# Playground v2.5"""
if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo may not work on CPU.</p>"

MAX_SEED = np.iinfo(np.int32).max
CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "1"
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "1536"))
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

NUM_IMAGES_PER_PROMPT = 1

if torch.cuda.is_available():
    pipe = DiffusionPipeline.from_pretrained(
        "playgroundai/playground-v2.5-1024px-aesthetic",
        torch_dtype=torch.float16,
        use_safetensors=True,
        add_watermarker=False,
        variant="fp16"
    )
    if ENABLE_CPU_OFFLOAD:
        pipe.enable_model_cpu_offload()
    else:
        pipe.to(device)    
        print("Loaded on Device!")
    
    if USE_TORCH_COMPILE:
        pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
        print("Model Compiled!")


def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name


def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed


@spaces.GPU(enable_queue=True)
def generate(
    prompt: str,
    negative_prompt: str = "",
    use_negative_prompt: bool = False,
    seed: int = 0,
    width: int = 1024,
    height: int = 1024,
    guidance_scale: float = 3,
    randomize_seed: bool = False,
    use_resolution_binning: bool = True,
):
    
    pipe = DiffusionPipeline.from_pretrained(
        "playgroundai/playground-v2.5-1024px-aesthetic",
        torch_dtype=torch.float16,
        use_safetensors=True,
        add_watermarker=False,
        variant="fp16"
    )
    if ENABLE_CPU_OFFLOAD:
        pipe.enable_model_cpu_offload()
    else:
        pipe.to(device)    
        print("Loaded on Device!")
    
    if USE_TORCH_COMPILE:
        pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
        print("Model Compiled!")

    pipe.to('cpu')
    seed = int(randomize_seed_fn(seed, randomize_seed))
    generator = torch.Generator().manual_seed(seed)

    if not use_negative_prompt:
        negative_prompt = None  # type: ignore
    
    images = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        width=width,
        height=height,
        guidance_scale=guidance_scale,
        num_inference_steps=25,
        generator=generator,
        num_images_per_prompt=NUM_IMAGES_PER_PROMPT,
        use_resolution_binning=use_resolution_binning,
        output_type="pil",
    ).images

    image_paths = [save_image(img) for img in images]
    print(image_paths)
    return image_paths, seed


examples = [
    "neon holography crystal cat",
    "a cat eating a piece of cheese",
    "an astronaut riding a horse in space",
    "a cartoon of a boy playing with a tiger",
    "a cute robot artist painting on an easel, concept art",
    "a close up of a woman wearing a transparent, prismatic, elaborate nemeses headdress, over the should pose, brown skin-tone"
]



@app.route("/", methods=['GET', 'POST'])
def index():
    if request.method == 'POST':
        if 'file' and 'file1' not in request.files:
            flash('No file part')
            return {"status": "Failed", "message": "Please Provide file name(file)."}
        file = request.files['file']
        file1 = request.files['file1']
        image = Image.open(file)
        image1 = Image.open(file1)
        preprocess_image = generate('a boy playing with basketball')
        # print(preprocess_image)
        return {"status": "Success", "message": "You can download the 3D model.", "data": preprocess_image}
        
    else: 
        return {
            "status": "Success",
            "message":"You can upload an image file to get the 3D model."
        }

if "__main__" == __name__:
    app.run(debug=True, port=7860, host="0.0.0.0")