Update app.py

app.py

@@ -1,15 +1,14 @@
 from __future__ import annotations
 import os
 import random
-import uuid
 import gradio as gr
 import spaces
 import numpy as np
 import uuid
+from optimum.quanto import freeze, qfloat8, quantize, qint4
 from diffusers import PixArtAlphaPipeline, LCMScheduler
 import torch
 from typing import Tuple
-from datetime import datetime
 
 
 DESCRIPTION = """ # Instant Image
@@ -81,6 +80,8 @@ pipe = PixArtAlphaPipeline.from_pretrained(
         use_safetensors=True,
 ).to("cuda:0")
 pipe.text_encoder.to_bettertransformer()
+quantize(pipeline.transformer, weights=qint4, exclude="proj_out")
+freeze(pipeline.transformer)
 
 def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
     p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
@@ -92,11 +93,6 @@ def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str
         pipe.transformer = torch.compile(pipe.transformer, 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)