Siyuan Li, Li Sun, Changxin Gao, Qiusheng Huang, Qingli Li, Xueqi Hu, Zhengyi Shi
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Reference-based Editing Figure 1. Image inversion and editing results of our model on CelebA-HQ dataset. From left to right, we show the inversion, label-based editing and reference-based editing. For the reference-based editing, the three columns are the source, reference and edit images, and each edit image takes the style of the reference while maintaining the source content.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.07932")
get_code_for_paper("2203.07932")
have("2203.07932")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.07932.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.07932)
Connect an agent — have() is free.