init

.gitignore

@@ -0,0 +1 @@
+venv

README copy.md

@@ -0,0 +1,12 @@
+---
+title: Ugen Image Captioning
+emoji: 📊
+colorFrom: green
+colorTo: purple
+sdk: gradio
+sdk_version: 4.12.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from uform import gen_model
+from PIL import Image
+import requests
+
+# Load the model and processor
+model = gen_model.VLMForCausalLM.from_pretrained("unum-cloud/uform-gen")
+processor = gen_model.VLMProcessor.from_pretrained("unum-cloud/uform-gen")
+
+
+def generate_caption(image, prompt):
+    # Process the image and the prompt
+    inputs = processor(text=prompt, images=image, return_tensors="pt", padding=True)
+
+    # Generate the output
+    outputs = model.generate(**inputs)
+    caption = processor.decode(outputs[0], skip_special_tokens=True)
+
+    return caption
+
+
+# Load the demo image
+demo_image = Image.open("jungle-glass.png")
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_caption,
+    inputs=[
+        gr.inputs.Image(type="pil", label="Upload Image", default=demo_image),
+        gr.inputs.Textbox(label="Prompt"),
+    ],
+    outputs=gr.outputs.Textbox(label="Generated Caption"),
+)
+
+# Launch the interface
+iface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+uform