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 🤗

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

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

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

Inference and fine-tuning examples for vision models from 🤗 Transformers

本项目以应用为主出发，结合了从基础的机器学习、深度学习到目标检测以及目前最新的大模型，采用目前成熟的 第三方库、开源预训练模型以及相关论文的最新技术，目的是记录学习的过程同时也进行分享以供更多人可以直接进行使用。

Official PyTorch implementation of the WACV 2025 Oral 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

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

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

Download flickr8k, flickr30k image caption datasets

Chitrarth: Bridging Vision and Language for a Billion People

Meme search and discovery engine using OpenAI CLIP and Salesforce BLIP

Fine-Tuning SigLIP 2 for Single/Multi-Label Image Classification

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.

Code for Post-hoc Probabilistic Vision-Language Models

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

Notes for the Vision Language Model implementation by Umar Jamil

Gender-Classifier-Mini is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify images based on gender using the SiglipForImageClassification architecture.