Initial gallery

.cursorignore

@@ -0,0 +1,2 @@
+# Environment variables
+.env

.gitignore

@@ -0,0 +1,24 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+.venv/
+venv/
+ENV/
+env/
+
+# Environment variables
+.env
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db

app.py

@@ -1,14 +1,109 @@
+from dotenv import load_dotenv
 import gradio as gr
-import spaces
-import torch
+from huggingface_hub import InferenceClient
+from io import BytesIO
+from os import path, unlink
+import pandas as pd
+from pandas import DataFrame
+from PIL.Image import Image, open as open_image
+import requests
+import tempfile
 
-zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+REQUEST_TIMEOUT = 45
 
-@spaces.GPU
-def greet(n):
-    print(zero.device) # <-- 'cuda:0' 🤗
-    return f"Hello {zero + n} Tensor"
+TEXT_TO_IMAGE_MODEL = "black-forest-labs/FLUX.1-dev"
+IMAGE_CLASSIFICATION_MODEL = "prithivMLmods/Trash-Net"
 
-demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
-demo.launch()
+# Load environment variables from .env file
+load_dotenv()
+
+client = InferenceClient()
+
+def save_image_to_temp_file(image: Image) -> str:
+    image_format = image.format if image.format else 'PNG'
+    format_extension = image_format.lower() if image_format else 'png'
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=f".{format_extension}")
+    temp_path = temp_file.name
+    temp_file.close()
+    image.save(temp_path, format=image_format)
+    return temp_path
+
+def text_to_image(prompt: str) -> Image:
+    return client.text_to_image(prompt, model=TEXT_TO_IMAGE_MODEL)
+
+def image_classification(image_url: str | None, uploaded_image: Image | None) -> tuple[Image | None, DataFrame]:
+    temp_file_path = None
+    try:
+        if uploaded_image is not None and image_url and image_url.strip():
+            raise gr.Error("Both an image URL and an uploaded image were provided. Please provide only one or the other.")
+        elif uploaded_image is not None:
+            temp_file_path = save_image_to_temp_file(uploaded_image)
+            classifications = client.image_classification(temp_file_path, model=IMAGE_CLASSIFICATION_MODEL)
+            image = None
+        elif image_url and image_url.strip():
+            try:
+                response = requests.get(image_url, timeout=REQUEST_TIMEOUT)
+                response.raise_for_status()
+                image = open_image(BytesIO(response.content))
+                temp_file_path = save_image_to_temp_file(image)
+                classifications = client.image_classification(temp_file_path, model=IMAGE_CLASSIFICATION_MODEL)
+            except Exception as e:
+                raise gr.Error(f"Failed to fetch image from URL: {str(e)}")
+        else:
+            raise gr.Error("Please either provide an image URL or upload an image.")
+        df = pd.DataFrame([
+            {"Label": classification.label, "Probability": f"{classification.score:.2%}"}
+            for classification in classifications
+        ])
+        return image, df
+    finally:
+        # Clean up temporary file.
+        if temp_file_path and path.exists(temp_file_path):
+            try:
+                unlink(temp_file_path)
+            except Exception:
+                pass # Ignore clean-up errors.
+
+with gr.Blocks(title="AI Building Blocks") as demo:
+    gr.Markdown("# AI Building Blocks")
+    gr.Markdown("A gallery of building blocks for building AI applications")
+    with gr.Tabs():
+        with gr.Tab("Text-to-image Generation"):
+            gr.Markdown("Generate an image from a text prompt.")
+            text_to_image_prompt = gr.Textbox(label="Prompt", value="A panda under a giant mushroom next to a pumpkin")
+            text_to_image_generate_button = gr.Button("Generate")
+            text_to_image_output = gr.Image(label="Image", type="pil")
+            text_to_image_generate_button.click(
+                fn=text_to_image,
+                inputs=text_to_image_prompt,
+                outputs=text_to_image_output
+            )
+        with gr.Tab("Image Classification"):
+            gr.Markdown("Classify a recyclable item as one of: cardboard, glass, metal, paper, plastic, or other using [Trash-Net](https://huggingface.co/prithivMLmods/Trash-Net).")
+            with gr.Row():
+                with gr.Column():
+                    image_classification_url_input = gr.Textbox(
+                        label="Image URL",
+                        value="https://campuslifeservices.ucsf.edu/upload/facilities/galleries/cardboard_0.jpg",
+                        placeholder="Enter the URL of the image to classify",
+                        scale=2
+                    )
+                    image_classification_image_preview = gr.Image(label="Image Preview", type="pil")
+                image_classification_upload_input = gr.Image(
+                    label="Or Upload Image",
+                    type="pil",
+                    scale=2
+                )
+            image_classification_button = gr.Button("Classify")
+            image_classification_output = gr.Dataframe(
+                label="Classification Results",
+                headers=["Label", "Probability"],
+                interactive=False
+            )
+            image_classification_button.click(
+                fn=image_classification,
+                inputs=[image_classification_url_input, image_classification_upload_input],
+                outputs=[image_classification_image_preview, image_classification_output]
+            )
+
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio>=5.49.1
+huggingface-hub>=1.0.1
+python-dotenv>=1.0.0
+pandas>=2.0.0
+pillow>=10.0.0
+requests>=2.31.0