Upload 4 files

README.md

@@ -1,12 +1,14 @@
 ---
-title: Art Analysis With Phi-4
-emoji: 🐢
-colorFrom: purple
-colorTo: gray
+title: Phi4 Multimodal
+emoji: 🦀
+colorFrom: yellow
+colorTo: pink
 sdk: gradio
-sdk_version: 5.20.1
+sdk_version: 5.19.0
 app_file: app.py
 pinned: false
+license: apache-2.0
+short_description: Space demoing Phi4 MultiModal
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,97 @@
+import gradio as gr
+from PIL import Image
+import torch
+from transformers import AutoModelForCausalLM, AutoProcessor
+import spaces
+
+# Define model path
+model_path = "microsoft/Phi-4-multimodal-instruct"
+
+# Load model and processor
+processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype="auto",
+    trust_remote_code=True,
+    _attn_implementation="eager",
+)
+
+# Define prompt structure
+user_prompt = "<|user|>"
+assistant_prompt = "<|assistant|>"
+prompt_suffix = "<|end|>"
+
+# Define inference function
+@spaces.GPU
+def analyze_artwork(file):
+    if not file:
+        return "Please upload an image of an artwork."
+    
+    # Custom prompt for artwork analysis
+    prompt = (
+        f"{user_prompt} You are an expert art historian and critic. Your task is to analyze the given artwork."
+        f" Provide a structured and insightful analysis based on the following points:\n\n"
+        f"1. **General Description**: Describe the colors, composition, and subject.\n"
+        f"2. **Artistic Style**: Identify the artistic movement (e.g., Impressionism, Surrealism).\n"
+        f"3. **Historical Context**: Discuss the period (e.g., Renaissance, Baroque) and cultural influences that influenced the artwork.\n"
+        f"4. **Symbolism & Meaning**: Interpret the messages and emotions conveyed.\n"
+        f"5. **Technical Analysis**: Examine brushwork, lighting, and composition.\n"
+        f"6. **Impact & Significance**: Explain the artwork’s relevance in the art world.\n\n"
+        f"Here is the artwork for analysis:\n"
+        f"<|image_1|>\n"
+        f"{prompt_suffix}{assistant_prompt}"
+    )
+    
+    # Open image from uploaded file
+    image = Image.open(file)
+    inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+    
+    # Generate response
+    with torch.no_grad():
+        generate_ids = model.generate(
+            **inputs,
+            max_new_tokens=1000,
+            num_logits_to_keep=0,
+            temperature=0.7,  
+            top_k=50,
+        )
+    generate_ids = generate_ids[:, inputs["input_ids"].shape[1]:]
+    response = processor.batch_decode(
+        generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )[0]
+    
+    return response
+
+# Gradio interface
+with gr.Blocks(title="Art Analysis with Phi-4") as demo:
+    gr.Markdown(
+        """
+        # 🎨 Art Analysis with Phi-4
+        Upload an **image** of an artwork, and get a detailed analysis by an AI art historian!  
+        Built with the microsoft/Phi-4-multimodal-instruct model.
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            image_input = gr.Image(label="Upload Artwork Image", type="filepath")
+            submit_btn = gr.Button("Analyze Artwork", variant="primary")
+        
+        with gr.Column(scale=2):
+            output_text = gr.Textbox(
+                label="Art Analysis Result",
+                placeholder="The AI's response will appear here...",
+                lines=20,
+                interactive=False,
+            )
+
+    # Connect the submit button
+    submit_btn.click(
+        fn=analyze_artwork,
+        inputs=[image_input],
+        outputs=output_text,
+    )
+
+# Launch the demo
+demo.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,11 @@
+gradio
+spaces
+requests
+torch
+pillow
+soundfile
+transformers
+torchvision
+scipy
+peft
+backoff