Update app.py

app.py

@@ -60,11 +60,11 @@ def generate(
     if torch.cuda.is_available():
 
         if not use_vae:  
-            pipe = DiffusionPipeline.from_pretrained(model, torch_dtype=torch.float16)
+            pipe = DiffusionPipeline.from_pretrained(model, torch_dtype=torch.float16, variant="fp16")
             
         if use_vae:
-            vae = AutoencoderKL.from_pretrained(vaecall, torch_dtype=torch.float16)
-            pipe = DiffusionPipeline.from_pretrained(model, vae=vae, torch_dtype=torch.float16)
+            vae = AutoencoderKL.from_pretrained(vaecall, torch_dtype=torch.float16, variant="fp16")
+            pipe = DiffusionPipeline.from_pretrained(model, vae=vae, torch_dtype=torch.float16, variant="fp16")
             
         if use_lora:
             pipe.load_lora_weights(lora)