Upload 2 files

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+import base64
+from io import BytesIO
+
+# Modell vorbereiten
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
+
+# Hilfsfunktion: Bild in base64 für HTML-Thumbnail umwandeln
+def image_to_base64_html(img):
+    buffered = BytesIO()
+    img.save(buffered, format="PNG")
+    img_str = base64.b64encode(buffered.getvalue()).decode()
+    html = f'<img src="data:image/png;base64,{img_str}" width="150"/>'
+    return html
+
+# Hauptfunktion: Bild → Beschreibung → beides in Chat
+def describe_image_with_thumbnail(image, history):
+    if image is None:
+        return history
+
+    # Beschreibung generieren
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    output = model.generate(**inputs)
+    caption = processor.decode(output[0], skip_special_tokens=True)
+
+    # Bild in HTML konvertieren
+    image_html = image_to_base64_html(image)
+
+    # Chatverlauf aktualisieren (Bild + Beschreibung)
+    history.append((image_html, caption))
+    return history
+
+# UI bauen
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 Bildbeschreibung-Chatbot mit Thumbnail-Vorschau")
+    chatbot = gr.Chatbot(label="Bilder-Chat")
+    with gr.Row():
+        image_input = gr.Image(type="pil", label="Bild hier hochladen")
+        send_btn = gr.Button("Bild analysieren")
+
+    send_btn.click(fn=describe_image_with_thumbnail, inputs=[image_input, chatbot], outputs=chatbot)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+gradio
+Pillow