Duplicate from A-Celsius/Caption-Generator

Co-authored-by: Akshay Chauhan <A-Celsius@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

README.md

@@ -0,0 +1,13 @@
+---
+title: Caption Generator
+emoji: 🦀
+colorFrom: purple
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.28.2
+app_file: app.py
+pinned: false
+duplicated_from: A-Celsius/Caption-Generator
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,48 @@
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+import gradio as gr
+
+model_name = "Salesforce/blip-image-captioning-base"
+
+caption_processor = BlipProcessor.from_pretrained(model_name)
+model = BlipForConditionalGeneration.from_pretrained(model_name)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def generate_captions(image, num_captions=5,size=(512, 512)):
+    image = image.resize(size)
+    if image.mode != 'RGB':
+        image = image.convert('RGB')
+    pixel_values = caption_processor(image, return_tensors='pt').to(device)
+    
+    caption_ids = model.generate(
+        **pixel_values, 
+        max_length=30,
+        num_beams=5,
+        num_return_sequences=num_captions,
+        temperature=1.0
+    )
+    
+    captions = [
+        caption_processor.decode(ids, skip_special_tokens=True) 
+        for ids in caption_ids
+    ]
+    
+    return captions
+
+from gradio.components import Image, Textbox,Slider
+
+interface = gr.Interface(
+    fn=generate_captions,
+    inputs=[
+        Image(type="pil", label="Input Image"),
+        Slider(minimum=1, maximum=5, step=1, label="Number of Captions")
+    ],
+    outputs=Textbox(type="text", label="Captions"),
+    title="Image Caption Generator",
+    description="AI tool that creates captions based on the image provided by the user.",
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,2 @@
+torch
+transformers