Update app.py

app.py

@@ -113,7 +113,7 @@ print('total upsampler parameters', sum(x.numel() for x in model_up.parameters()
 
 
 
-def get_images(batch: th.Tensor, output_size=(5, 5)):
+def get_images(batch: th.Tensor, output_size=(256, 256)):
     """ Display a batch of images inline. """
     scaled = ((batch + 1)*127.5).round().clamp(0,255).to(th.uint8).cpu()
     reshaped = scaled.permute(2, 0, 3, 1).reshape([batch.shape[2], -1, 3])
@@ -121,12 +121,7 @@ def get_images(batch: th.Tensor, output_size=(5, 5)):
     image = ImageOps.fit(image, output_size, Image.ANTIALIAS)
     return image
 
-def get_images(batch: th.Tensor):
-    """ Display a batch of images inline. """
-    scaled = ((batch + 1)*127.5).round().clamp(0,255).to(th.uint8).cpu()
-    reshaped = scaled.permute(2, 0, 3, 1).reshape([batch.shape[2], -1, 3])
-    image = Image.fromarray(reshaped.numpy())
-    return image
+
     
 # Create a classifier-free guidance sampling function
 guidance_scale = 8.0
@@ -257,7 +252,7 @@ examples =["melanoma"]
 
 iface = gr.Interface(fn=sample, 
                      inputs=gr.inputs.Textbox(label='Which dermoscopic entity would you like to see? Choose one of the following one: "melanoma", "melanocytic nevi", "Actinic keratoses and intraepithelial carcinoma / Bowen disease, "benign keratosis-like lesions (solar lentigines / seborrheic keratoses and lichen-planus like keratoses", "basal cell carcinoma", "dermatofibroma", "vascular lesions"'), 
-                     outputs=gr.outputs.Image(type="pil", label="Model input + completions", width=256, height=256),
+                     outputs=gr.outputs.Image(type="pil", label="Model input + completions", width=64, height=64),
                      title=title,
                      description=description,
                      article=article,