Update app.py

app.py

@@ -13,6 +13,9 @@ from kolors.models.tokenization_chatglm import ChatGLMTokenizer
 from diffusers import UNet2DConditionModel, AutoencoderKL
 from diffusers import EulerDiscreteScheduler
 
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 # Initialize models
 device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.float16