SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.06285 · 2023

DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Text-driven image manipulation remains challenging in training or inference flexibility. Conditional generative models depend heavily on expensive annotated training data. Meanwhile, recent frameworks, which leverage pre-trained vision-language models, are limited by either per text-prompt optimization or inference-time hyper-parameters tuning. In this work, we propose a novel framework named \textit{DeltaEdit} to address these problems. Our key idea is to investigate and identify a space, namely delta image and text space that has well-aligned distribution between CLIP visual feature differences of two images and CLIP textual embedding differences of source and target texts. Based on the CLIP delta space, the DeltaEdit network is designed to map the CLIP visual features differences to the editing directions of StyleGAN at training phase. Then, in inference phase, DeltaEdit predicts the StyleGAN's editing directions from the differences of the CLIP textual features. In this way, DeltaEdit is trained in a text-free manner. Once trained, it can well generalize to various text prompts for zero-shot inference without bells and whistles.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.06285")
get_code_for_paper("2303.06285")
have("2303.06285")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.06285.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.06285.svg)](https://syntology.ai/paper/2303.06285)

Connect an agent — have() is free.