2023/12/13 by Zhenduo Zhang, Bowen Zhang, Zhang, Zhenduo +3
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face recognition and analysis #Facial Nerve Paralysis Treatment and Research #Herpesvirus Infections and Treatments
paper · pdf · doi:10.48550/arxiv.2312.07879
openalex publication_date 2023/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Current text-to-image editing models often encounter challenges with smoothly manipulating multiple attributes using a single instruction. Taking inspiration from the Chain-of-Thought prompting technique utilized in language models, we present an innovative concept known as Chain-of-Instruct Editing (CoIE), which enhances the capabilities of these models through step-by-step editing using a series of instructions. In particular, in the context of face manipulation, we leverage the contextual learning abilities of a pretrained Large Language Model (LLM), such as GPT-4, to generate a sequence of instructions from the original input, utilizing a purpose-designed 1-shot template. To further improve the precision of each editing step, we conduct fine-tuning on the editing models using our self-constructed instruction-guided face editing dataset, Instruct-CelebA. And additionally, we incorporate a super-resolution module to mitigate the adverse effects of editability and quality degradation. Experimental results across various challenging cases confirm the significant boost in multi-attribute facial image manipulation using chain-of-instruct editing. This is evident in enhanced editing success rates, measured by CLIPSim and Coverage metrics, improved by 17.86% and 85.45% respectively, and heightened controllability indicated by Preserve L1 and Quality metrics, improved by 11.58% and 4.93% respectively.