paper-with-me

홈 › Papers

CoIE: Chain-of-Instruct Editing for Multi-Attribute Face Manipulation

2023-12-13 · Zhenduo Zhang, Bo-Wen Zhang, Guang Liu

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.

📄 PDF Abstract BibTeX arXiv:2312.07879

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImage ManipulationLanguage ModellingLarge Language ModelSuper-Resolution

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Instruction-based Image Editing with Planning, Reasoning, and Generation

2026-02-26 · Liya Ji, Chenyang Qi, Qifeng Chen arxiv

Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large l…

Object SegmentationScene UnderstandingImage Editing

EmoKGEdit: Training-free Affective Injection via Visual Cue Transformation

2026-01-18 · Jing Zhang, Bingjie Fan arxiv

Existing image emotion editing methods struggle to disentangle emotional cues from latent content representations, often yielding weak emotional expression and distorted visual structures. To bridge this gap, we propose …

NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image Editing

2025-11-28 · Zhenyu Xu, Xiaoqi Shen, Haotian Nan, Xinyu Zhang arxiv

Instruction-based image editing enables intuitive manipulation through natural language commands. However, text instructions alone often lack the precision required for fine-grained control over edit intensity. We introd…

Image ManipulationImage Editing

ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies

2025-06-15 · Chenglin Wang, Yucheng Zhou, Qianning Wang, Zhe Wang 외

Text-driven image editing has achieved remarkable success in following single instructions. However, real-world scenarios often involve complex, multi-step instructions, particularly ``chain'' instructions where operatio…

Benchmarking

SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control

2025-11-12 · Arman Zarei, Samyadeep Basu, Mobina Pournemat, Sayan Nag 외 arxiv

Instruction-based image editing models have recently achieved impressive performance, enabling complex edits to an input image from a multi-instruction prompt. However, these models apply each instruction in the prompt w…

Text-to-Image GenerationImage ManipulationImage Editing