Update app.py

app.py

@@ -25,7 +25,6 @@ CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1")
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4192"))
 USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
 ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"
-PORT = int(os.getenv("DEMO_PORT", "15432"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
@@ -93,15 +92,9 @@ if torch.cuda.is_available():
         use_safetensors=True,
     )
 
-    if os.getenv('CONSISTENCY_DECODER', False):
-        print("Using DALL-E 3 Consistency Decoder")
-        pipe.vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16)
+    pipe.vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16)
 
-    if ENABLE_CPU_OFFLOAD:
-        pipe.enable_model_cpu_offload()
-    else:
-        pipe.to(device)
-        print("Loaded on Device!")
+    pipe.to(device)
         
     # speed-up T5
     pipe.text_encoder.to_bettertransformer()
@@ -131,7 +124,7 @@ def generate(
         seed: int = 0,
         width: int = 1024,
         height: int = 1024,
-        inference_steps: int = 8,
+        inference_steps: int = 12,
         randomize_seed: bool = False,
         use_resolution_binning: bool = True,
         progress=gr.Progress(track_tqdm=True),