Upload 2 files

app.py

@@ -1,70 +1,41 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+
+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)
+
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+gpt2_model = GPT2LMHeadModel.from_pretrained("gpt2").to(device)
+
+def generate_paragraph(image):
+    if image.mode != 'RGB':
+        image = image.convert('RGB')
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    output_ids = model.generate(**inputs, max_length=50)
+    caption = processor.decode(output_ids[0], skip_special_tokens=True)
+
+    prompt = f"Write a detailed paragraph about this image: {caption}\n\nDetails:"
+    tokens = tokenizer.encode(prompt, return_tensors='pt').to(device)
+    outputs = gpt2_model.generate(tokens, max_length=150, num_beams=5, no_repeat_ngram_size=2, early_stopping=True, pad_token_id=tokenizer.eos_token_id)
+    paragraph = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Post-process to avoid repeating the prompt
+    if paragraph.lower().startswith(prompt.lower()):
+        paragraph = paragraph[len(prompt):].strip()
+
+    return paragraph
+
+iface = gr.Interface(
+    fn=generate_paragraph,
+    inputs=gr.Image(type="pil"),
+    outputs="textbox",
+    title="Image Paragraph Description Generator",
+    description="Upload an image to get a detailed paragraph description generated."
+)
+
+iface.launch()

requirements.txt

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