Papers › Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

Text-Free Learning of a Natural Language Interface for Pretrained Face Generators

8 Sep 2022arXiv:2209.03953archive 2025-07-28

Xiaodan Du, Raymond A. Yeh, Nicholas Kolkin, Eli Shechtman, Greg Shakhnarovich

We propose Fast text2StyleGAN, a natural language interface that adapts pre-trained GANs for text-guided human face synthesis. Leveraging the recent advances in Contrastive Language-Image Pre-training (CLIP), no text data is required during training. Fast text2StyleGAN is formulated as a conditional variational autoencoder (CVAE) that provides extra control and diversity to the generated images at test time. Our model does not require re-training or fine-tuning of the GANs or CLIP when encountering new text prompts. In contrast to prior work, we do not rely on optimization at test time, making our method orders of magnitude faster than prior work. Empirically, on FFHQ dataset, our method offers faster and more accurate generation of images from natural language descriptions with varying levels of detail compared to prior work.

PaperPDFCode

Code

duxiaodan/fast_text2stylegan officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityFace Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIPTest

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections