paper-with-me

Papers

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 introduce NumeriKontrol, a framework that allows users to precisely adjust image attributes using continuous scalar values with common units. NumeriKontrol encodes numeric editing scales via an effective Numeric Adapter and injects them into diffusion models in a plug-and-play manner. Thanks to a task-separated design, our approach supports zero-shot multi-condition editing, allowing users to specify multiple instructions in any order. To provide high-quality supervision, we synthesize precise training data from reliable sources, including high-fidelity rendering engines and DSLR cameras. Our Common Attribute Transform (CAT) dataset covers diverse attribute manipulations with accurate ground-truth scales, enabling NumeriKontrol to function as a simple yet powerful interactive editing studio. Extensive experiments show that NumeriKontrol delivers accurate, continuous, and stable scale control across a wide range of attribute editing scenarios. These contributions advance instruction-based image editing by enabling precise, scalable, and user-controllable image manipulation.

📄 PDF Abstract BibTeX arXiv:2511.23105

Code (0)

등록된 구현이 없습니다.

Tasks

Image ManipulationImage Editing

Similar Papers 제목 키워드 기반

Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers

2025-05-07 · Divyansh Srivastava, Xiang Zhang, He Wen, Chenru Wen 외

We present Lay-Your-Scene (shorthand LayouSyn), a novel text-to-layout generation pipeline for natural scenes. Prior scene layout generation methods are either closed-vocabulary or use proprietary large language models f…

Image GenerationLayout Generation

Denoising Diffusion-Based Control of Nonlinear Systems

2024-02-03 · Karthik Elamvazhuthi, Darshan Gadginmath, Fabio Pasqualetti

We propose a novel approach based on Denoising Diffusion Probabilistic Models (DDPMs) to control nonlinear dynamical systems. DDPMs are the state-of-art of generative models that have achieved success in a wide variety o…

Denoising

Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers

2025-05-27 · Charles London, Varun Kanade

Pause tokens, simple filler symbols such as "...", consistently improve Transformer performance on both language and mathematical tasks, yet their theoretical effect remains unexplained. We provide the first formal separ…

SHIFT: Steering Hidden Intermediates in Flow Transformers

2026-04-10 · Nina Konovalova, Andrey Kuznetsov, Aibek Alanov arxiv

Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong prompt adherence while producing high-quality samples. We propose SHIFT…

Image Generation

Transformers Can Compose Skills To Solve Novel Problems Without Finetuning

2021-09-17 · ACL ARR September 2021 9 · Anonymous

It is possible to achieve improved prediction performance with Transformers on unseen datasets by adding disparate new training tasks to an existing multitask training regime. We demonstrate that this can be attributed t…

Question AnsweringSemantic SimilaritySemantic Textual Similarity