Upload folder using huggingface_hub

README.md

@@ -1,12 +1,25 @@
 ---
 title: Image Detective
-emoji: 💻
+emoji: 🔍
 colorFrom: blue
-colorTo: pink
+colorTo: blue
 sdk: gradio
-sdk_version: 6.0.2
+sdk_version: "6.0.2"
 app_file: app.py
 pinned: false
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 🔍 Image Detective
+
+Classify images into any categories you define using CLIP zero-shot classification.
+
+## Features
+
+- Upload any image
+- Define custom categories on the fly
+- No model downloads - uses API
+
+## Setup
+
+Add your `HF_TOKEN` as a Secret in Space Settings.

app.py

@@ -0,0 +1,48 @@
+import os
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+# Get token from environment (set in HF Space secrets)
+HF_TOKEN = os.environ.get("HF_TOKEN", "")
+client = InferenceClient(token=HF_TOKEN) if HF_TOKEN else InferenceClient()
+
+
+def classify(image, labels_text: str) -> dict:
+    """Classify image against user-provided labels."""
+    if image is None:
+        return {}
+    labels = [l.strip() for l in labels_text.split(",") if l.strip()]
+    if not labels:
+        labels = ["cat", "dog", "bird", "car", "person"]
+    
+    try:
+        results = client.zero_shot_image_classification(
+            image,
+            candidate_labels=labels,
+            model="openai/clip-vit-base-patch32",
+        )
+        return {r.label: r.score for r in results}
+    except Exception as e:
+        return {"Error": str(e)}
+
+
+with gr.Blocks(title="Image Detective") as demo:
+    gr.Markdown("# 🔍 Image Detective\nUpload an image and define your own categories!")
+
+    with gr.Row(equal_height=True):
+        with gr.Column(scale=1):
+            img_input = gr.Image(type="pil", label="Upload or drop an image")
+            labels_input = gr.Textbox(
+                label="Categories (comma-separated)",
+                placeholder="cat, dog, bird, car",
+                value="cat, dog, bird, car, person",
+            )
+            btn = gr.Button("Classify!", variant="primary")
+        with gr.Column(scale=1):
+            output = gr.Label(label="Predictions", num_top_classes=5)
+
+    btn.click(classify, inputs=[img_input, labels_input], outputs=output)
+    labels_input.submit(classify, inputs=[img_input, labels_input], outputs=output)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=6.0.0
+huggingface_hub>=0.23.0
+pillow>=10.0.0
+