fix: add png handling for LazyLoadingImage (#203)

Loading png images for captioning will cause the following error since PIL loads png images in RGBA mode.

```python
  File "./miniconda3/lib/python3.8/site-packages/torchvision/transforms/functional_tensor.py", line 940, in normalize
    return tensor.sub_(mean).div_(std)
RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
```

imaginairy/enhancers/describe_image_blip.py

@@ -36,6 +36,7 @@ def blip_model():
 
 def generate_caption(image, min_length=30):
     """Given an image, return a caption."""
+    image = image.convert("RGB")
     gpu_image = (
         transforms.Compose(
             [