Amit H. Bermano

Excited to introduce our new work: ImageRAG 🖼️✨ rotem-shalev.github.io/ImageRAG We enhance off-the-shelf generative models with Retrieval-Augmented Generation (RAG) for unknown concept generation, using a VLM-based approach that’s easy to integrate with new & existing models! [1/3]

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion abs: arxiv.org/abs/2208.01618 “Textual Inversions”, operates by inverting the concepts into new pseudo-words within the textual embedding space of a pre-trained text-to-image model

CLIPasso: Semantically-Aware Object Sketching abs: arxiv.org/abs/2202.05822 project page: clipasso.github.io/clipasso/

MotionCLIP: Exposing Human Motion Generation to CLIP Space abs: arxiv.org/abs/2203.08063 project page: guytevet.github.io/motionclip-pag…