Upload app.py

app.py

@@ -644,17 +644,17 @@ with EmptyInitWrapper():
     sd = {k.replace("model.", ""): v for k, v in sd.items()}
     result = model.load_state_dict(sd)
     
-@spaces.GPU(duration=70)
-@torch.no_grad()
+@spaces.GPU(duration=120)
+@torch.inference_mode()
 def generate_image(
-    prompt, neg_prompt,num_steps ,width, height, guidance, seed,
+    prompt, neg_prompt, num_steps ,width, height, guidance, seed,
     do_img2img, init_image, image2image_strength, resize_img,
     progress=gr.Progress(track_tqdm=True),
 ):
     if seed == 0:
         seed = int(random.random() * 1000000)
         
-    device = "cuda" if torch.cuda.is_available() else "cpu"
+    #device = "cuda" if torch.cuda.is_available() else "cpu"
     torch_device = torch.device(device)
         
     if do_img2img and init_image is not None:
@@ -709,7 +709,7 @@ def create_demo():
                 height = gr.Slider(minimum=128, maximum=2048, step=64, label="Height", value=1024)
                 guidance = gr.Slider(minimum=0.0, maximum=25.0, step=0.1, label="Guidance", value=3.5)
                 seed = gr.Number(label="Seed", precision=-1)
-                do_img2img = gr.Checkbox(label="Image to Image", value=False)
+                do_img2img = gr.Checkbox(label="Image to Image", value=False, visible=False)
                 init_image = gr.Image(label="Input Image", visible=False)
                 image2image_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label="Noising strength", value=0.8, visible=False)
                 resize_img = gr.Checkbox(label="Resize image", value=True, visible=False)