app

app.py

@@ -3,7 +3,7 @@ import open_clip
 
 
 model, _, transform = open_clip.create_model_and_transforms(
-    "coca_ViT-B-32",
+    "coca_ViT-L-14",
     pretrained="laion2B-s13B-b90k-mscoco-2014.pt"
 )
 
@@ -12,5 +12,5 @@ def output_generate(image):
     generated = model.generate(im)
     return open_clip.decode(generated).split("<end_of_text>")[0].replace("<start_of_text>", "")
 
-iface = gr.Interface(fn=output_generate, inputs=gr.image(type="pil"), outputs="text")
+iface = gr.Interface(fn=output_generate, inputs=gr.Image(type="pil"), outputs="text")
 iface.launch()