cene555/ruCLIP-SB
RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and rearranging captions and pictures. Unlike other versions of the model we use BERT for text encoder and SWIN transformer for image encoder.
This tool helps you analyze and organize visual content with accompanying text descriptions in Russian. You provide images and their Russian captions, and it calculates how similar each image is to a given text, or how well captions match pictures. This is useful for anyone working with large collections of Russian-language images and descriptions, such as content managers, archivists, or e-commerce specialists.
No commits in the last 6 months.
Use this if you need to quickly find Russian images based on text descriptions or sort Russian image-caption pairs by relevance.
Not ideal if your primary need is for non-Russian language content analysis or if you require fine-grained object detection within images.
Stars
14
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cene555/ruCLIP-SB"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ClipsAI/clipsai
Clips AI is an open-source Python library that automatically converts long videos into clips.
ai-forever/ru-clip
CLIP implementation for Russian language
patrickjohncyh/fashion-clip
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Lednik7/CLIP-ONNX
It is a simple library to speed up CLIP inference up to 3x (K80 GPU)
suinleelab/CellCLIP
[NeurIPS 2025] CellCLIP – Learning Perturbation Effects in Cell Painting via Text-Guided...