One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations

Chen, Yibing Song, Jue Wang, Chun Yuan, Xintong Han, Yiming Zhu, Hongyu Liu, Ziyang Yuan

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

kumapowerliu/ffclip — 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

ment, we inject semantics from text prompt embeddings to the StyleGAN latent space. For one type of image (e.g., 'human portrait'), one FFCLIP model can be learned to handle free-form text prompts. Meanwhile, we observe that although each training text prompt only contains a single semantic meaning, FFCLIP can leverage text prompts with multiple semantic meanings for image manipulation. In the experiments, we evaluate FFCLIP on three types of images (i.e., 'human portraits', 'cars', and 'churches'). Both visual and numerical results show that FFCLIP effectively produces semantically accurate and visually realistic images.

For agents

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

get_harvested_code_for_paper("2210.07883")
get_code_for_paper("2210.07883")
have("2210.07883")

Connect an agent — have() is free.