metadata
license: mit
datasets:
- laion/laion-art
- rafaelpadilla/coco2017
language:
- en
metrics:
- bleu
- rouge
- meteor
base_model:
- Salesforce/blip-image-captioning-base
- HuggingFaceTB/SmolLM3-3B
pipeline_tag: image-to-text
library_name: transformers
tags:
- image-to-text
- image-captioning
- AI
🧠 Image-to-Prompt Model
This is a simple and effective model that generates text prompts from uploaded images using BLIP + Transformers.
It uses Salesforce/blip-image-captioning-base under the hood and is optimized for use with Streamlit.
🔍 Example
Upload an image of a mountain and get a prompt like:
“A scenic view of snowy mountains under a clear blue sky.”
🧪 How to Use
from model import ImagePromptModel
model = ImagePromptModel()
result = model.generate_prompt("your_image.jpg")
print(result)