[ICML'24 Oral] "MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions"

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

[SIGIR'2024 Best Paper Honorable Mention] Official repository for "LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval"

SEED-Story is a JAX/Flax implementation of a multimodal story generation model based on the paper "SEED-Story: Multimodal Long Story Generation with Large Language Model". This model combines visio…

SEED-Story: Multimodal Long Story Generation with Large Language Model

Collection of Composed Image Retrieval (CIR) papers.

A ComfyUI extension for chatting with your images with LLaVA. Runs locally, no external services, no filter.

Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers" (ECCV 2024)