Update app.py

app.py

@@ -1,10 +1,10 @@
+import spaces
 import os
 import gc
 import gradio as gr
 import numpy as np
 import torch
 import json
-import spaces
 import config
 import utils
 import logging
@@ -21,7 +21,7 @@ if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU. </p>"
 IS_COLAB = utils.is_google_colab() or os.getenv("IS_COLAB") == "1"
 HF_TOKEN = os.getenv("HF_TOKEN")
-CACHE_EXAMPLES = 'lazy' if torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES") == "1" else False
+CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES") == "0"
 MIN_IMAGE_SIZE = int(os.getenv("MIN_IMAGE_SIZE", "512"))
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "2048"))
 USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE") == "1"
@@ -30,11 +30,12 @@ OUTPUT_DIR = os.getenv("OUTPUT_DIR", "./outputs")
 
 MODEL = os.getenv(
     "MODEL",
-    "https://huggingface.co/cagliostrolab/animagine-xl-3.1/blob/main/animagine-xl-3.1.safetensors",
+    "cagliostrolab/animagine-xl-3.1",
 )
 
 torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
+torch.backends.cuda.matmul.allow_tf32 = True
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
@@ -49,7 +50,7 @@ def load_pipeline(model_name):
         if MODEL.endswith(".safetensors")
         else StableDiffusionXLPipeline.from_pretrained
     )
-
+    
     pipe = pipeline(
         model_name,
         vae=vae,
@@ -392,4 +393,4 @@ with gr.Blocks(css="style.css", theme="NoCrypt/miku@1.2.1") as demo:
     )
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch(debug=IS_COLAB, share=IS_COLAB)
+    demo.queue(max_size=20).launch(debug=IS_COLAB, share=IS_COLAB)