E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance

no code implementations • 15 Mar 2024 • Tianrui Huang, Pu Cao, Lu Yang, Chun Liu, Mengjie Hu, Zhiwei Liu, Qing Song

Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications.

Text-based Image Editing

Controllable Generation with Text-to-Image Diffusion Models: A Survey

1 code implementation • 7 Mar 2024 • Pu Cao, Feng Zhou, Qing Song, Lu Yang

In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions.

Denoising

Concept-centric Personalization with Large-scale Diffusion Priors

1 code implementation • 13 Dec 2023 • Pu Cao, Lu Yang, Feng Zhou, Tianrui Huang, Qing Song

In this work, we present the task of customizing large-scale diffusion priors for specific concepts as concept-centric personalization.

Diffusion Personalization

What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion

2 code implementations • 28 Jan 2023 • Pu Cao, Lu Yang, Dongxv Liu, Xiaoya Yang, Tianrui Huang, Qing Song

To tackle this problem, we introduce Domain-Specific Hybrid Refinement (DHR), which draws on the advantages and disadvantages of two mainstream refinement techniques to maintain editing ability with fidelity improvement.

LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space

1 code implementation • 26 Sep 2022 • Pu Cao, Lu Yang, Dongxu Liu, Zhiwei Liu, Shan Li, Qing Song

In this work, we first point out that these two characteristics are related to the degree of alignment (or disalignment) of the inverse codes with the synthetic distribution.