Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗

[NeurIPS 2024] AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

Official PyTorch implementation of the WACV 2025 paper "Composed Image Retrieval for Training-FREE DOMain Conversion".

Low-latency ONNX and TensorRT based zero-shot classification and detection with contrastive language-image pre-training based prompts

A minimal, but effective implementation of CLIP (Contrastive Language-Image Pretraining) in PyTorch

Official repository of "TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models".

Download flickr8k, flickr30k image caption datasets

Este proyecto presenta una solución de Computer Vision para la detección y clasificación de objetos en imágenes, las cuales son extraídas como frames de vídeos. Utiliza el modelo FastSAM para la detección de objetos, y para la clasificación, emplea embeddings que pueden ser generados mediante dos modelos distintos: CLIP o SigLIP.

Meme search and discovery engine using OpenAI CLIP and Salesforce BLIP

A simple open-sourced SigLIP model finetuned on Genshin Impact's image-text pairs.

Implementation of PaliGemma

Notes for the Vision Language Model implementation by Umar Jamil

Korean version of CLIP which achieves Korean cross-modal retrieval and representation generation.

Framework for learning multi-domain image embeddings suitable for multi-domain image retrieval at instance-level

Web scraper for Wildberries + simple vectorization/multimodal embedding workflow

Training a clip model for vietnamese text