Anycost GANs for Interactive Image Synthesis and Editing

Ji Lin, Song Han, Richard Zhang, Jun-Yan Zhu, Frieder Ganz

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repository	Role	Ran
mit-han-lab/anycost-gan	—	0 of 1

Function	Status	Where it lives
Generator	Not yet run	mit-han-lab/anycost-gan/models/anycost_gan.py code served (permissive licence) · get_code("c456090ba2fac723")

Repositories linked to this paper

mit-han-lab/anycost-gan — marked official in Papers with Code; named in the paper

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

Abstract

tency requirements. When deployed on desktop CPUs and edge devices, our model can provide perceptually similar previews at 6-12× speedup, enabling interactive image editing. The code and demo are publicly available. * 1024-resolution StyleGAN2 has 144G MACs, while 256-resolution model has 85G MACs.

For agents

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

get_harvested_code_for_paper("2103.03243")
get_code_for_paper("2103.03243")
have("2103.03243")

Connect an agent — have() is free.