aavetis commited on
Commit
582a256
1 Parent(s): cdcc865

change input

Browse files
Files changed (1) hide show
  1. app.py +2 -8
app.py CHANGED
@@ -1,13 +1,11 @@
1
  import gradio as gr
2
  from uform import gen_model
3
  from PIL import Image
4
- import requests
5
 
6
  # Load the model and processor
7
  model = gen_model.VLMForCausalLM.from_pretrained("unum-cloud/uform-gen")
8
  processor = gen_model.VLMProcessor.from_pretrained("unum-cloud/uform-gen")
9
 
10
-
11
  def generate_caption(image, prompt):
12
  # Process the image and the prompt
13
  inputs = processor(text=prompt, images=image, return_tensors="pt", padding=True)
@@ -18,18 +16,14 @@ def generate_caption(image, prompt):
18
 
19
  return caption
20
 
21
-
22
  # Load the demo image
23
  demo_image = Image.open("jungle-glass.png")
24
 
25
  # Define the Gradio interface
26
  iface = gr.Interface(
27
  fn=generate_caption,
28
- inputs=[
29
- gr.inputs.Image(type="pil", label="Upload Image", default=demo_image),
30
- gr.inputs.Textbox(label="Prompt"),
31
- ],
32
- outputs=gr.outputs.Textbox(label="Generated Caption"),
33
  )
34
 
35
  # Launch the interface
 
1
  import gradio as gr
2
  from uform import gen_model
3
  from PIL import Image
 
4
 
5
  # Load the model and processor
6
  model = gen_model.VLMForCausalLM.from_pretrained("unum-cloud/uform-gen")
7
  processor = gen_model.VLMProcessor.from_pretrained("unum-cloud/uform-gen")
8
 
 
9
  def generate_caption(image, prompt):
10
  # Process the image and the prompt
11
  inputs = processor(text=prompt, images=image, return_tensors="pt", padding=True)
 
16
 
17
  return caption
18
 
 
19
  # Load the demo image
20
  demo_image = Image.open("jungle-glass.png")
21
 
22
  # Define the Gradio interface
23
  iface = gr.Interface(
24
  fn=generate_caption,
25
+ inputs=[gr.Image(type="pil", label="Upload Image", default=demo_image), gr.Textbox(label="Prompt")],
26
+ outputs=gr.Textbox(label="Generated Caption"),
 
 
 
27
  )
28
 
29
  # Launch the interface