Text2LIVE: Text-Driven Layered Image and Video Editing. A new zero shot technique to edit the appearances of images and video!

• Text2LIVE

  2 849 0.0 Python

  Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)

"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.   Semi-Transparent Effects Text2LIVE successfully augments the input scene with complex semi-transparent effects without changing irrelevant content in the image." demo site: https://text2live.github.io arxiv: https://arxiv.org/abs/2204.02491 github: https://github.com/omerbt/Text2LIVE

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project