This work presents AnyDoor a diffusion-based image generator with the power to teleport
target objects to new scenes at user-specified locations with desired shapes. Instead of …

Humans can easily solve multimodal tasks in context with only a few demonstrations or
simple instructions which current multimodal systems largely struggle to imitate. In this work …

Recent advances in personalized image generation have enabled pre-trained text-to-image
models to learn new concepts from specific image sets. However these methods often …

This paper presents DreamLLM, a learning framework that first achieves versatile
Multimodal Large Language Models (MLLMs) empowered with frequently overlooked …

Abstract Large-scale Text-to-Image (T2I) models have rapidly gained prominence across
creative fields generating visually compelling outputs from textual prompts. However …

Abstract Contrastive Language-Image Pre-training (CLIP) plays an essential role in
extracting valuable content information from images across diverse tasks. It aligns textual …

We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research
and applications. LAVIS aims to serve as a one-stop comprehensive library that brings …

Abstract Multimodal Large Language Models (MLLMs) have excelled in 2D image-text
comprehension and image generation but their understanding of the 3D world is notably …

Text-driven video generation witnesses rapid progress. However merely using text prompts
is not enough to depict the desired subject appearance that accurately aligns with users' …

Recent progress in personalized image generation using diffusion models has been
significant. However, development in the area of open-domain and non-fine-tuning …