Upload 2 files

app.py

@@ -53,10 +53,12 @@ from diffusers import FluxPipeline
 # import urllib.parse
 import subprocess
 
-subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)
-
+IS_ZEROGPU = os.getenv("SPACES_ZERO_GPU", False)
+if IS_ZEROGPU:
+    subprocess.run("rm -rf /data-nvme/zerogpu-offload/*", env={}, shell=True)
+    torch.backends.cuda.matmul.allow_tf32 = True
 ImageFile.LOAD_TRUNCATED_IMAGES = True
-torch.backends.cuda.matmul.allow_tf32 = True
+
 # os.environ["PYTORCH_NO_CUDA_MEMORY_CACHING"] = "1"
 print(os.getenv("SPACES_ZERO_GPU"))
 
@@ -893,7 +895,7 @@ with gr.Blocks(theme='NoCrypt/miku@>=1.2.2', elem_id="main", fill_width=True, cs
                         history_clear_button.click(lambda: ([], []), None, [history_gallery, history_files], queue=False, show_api=False)
 
                     with gr.Row(equal_height=False, variant="default"):
-                        gpu_duration_gui = gr.Number(minimum=5, maximum=240, value=59, show_label=False, container=False, info="GPU time duration (seconds)")
+                        gpu_duration_gui = gr.Number(minimum=5, maximum=240, value=20, show_label=False, container=False, info="GPU time duration (seconds)")
                         with gr.Column():
                             verbose_info_gui = gr.Checkbox(value=False, container=False, label="Status info")
                             load_lora_cpu_gui = gr.Checkbox(value=False, container=False, label="Load LoRAs on CPU")