1. [Publications](/publications)
2. Text2LIVE: Text-Driven Layered Image and Video Editing
 
 # Text2LIVE: Text-Driven Layered Image and Video Editing

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 We present a method for zero-shot, text-driven appearance manipulation in natural images and videos. Specifically, given an input image or video and a target text prompt, our goal is to edit the appearance of existing objects (e.g., object's texture) or augment the scene with new visual effects (e.g., smoke, fire) in a semantically meaningful manner. Our framework trains a generator using an *internal dataset* of training examples, extracted from a single input (image or video and target text prompt), while leveraging an *external* pre-trained CLIP model to establish our losses. Rather than directly generating the edited output, our key idea is to generate an *edit layer* (color+opacity) that is composited over the original input. This allows us to constrain the generation process and maintain high fidelity to the original input via novel text-driven losses that are applied directly to the edit layer. Our method neither relies on a pre-trained generator nor requires user-provided edit masks. Thus, it can perform localized, semantic edits on high-resolution natural images and videos across a variety of objects and scenes.



 ## Authors



Omer Bar-Tal (Weizmann Institute of Science)

Dolev Ofri-Amar (Weizmann Institute of Science)

 Rafail Fridman (Weizmann Institute of Science)

[Yoni Kasten](/person/yoni-kasten)

Tali Dekel (Weizmann Institute of Science)

 

 

 ## Publication Date



Sunday, October 23, 2022

 

 ## Published in



[ECCV 2022](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136750705.pdf)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

 

 

 ## External Links



[Project Page](https://text2live.github.io/)