10 papers · 1 filter
Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System
Mengwei Ren, Xuaner Zhang, Zhihao Xia
Generative image models can now produce high-quality images, follow complex instructions, and support precise edits, but they still struggle to preserve who or what is being depict…
TokenLight: Precise Lighting Control in Images using Attribute Tokens
Sumit Chaturvedi, Yannick Hold-Geoffroy, Mengwei Ren +5
This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a co…
How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation
Haoyu Chen, Qing Liu, Yuqian Zhou +7
Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffe…
A Unified and Controllable Framework for Layered Image Generation with Visual Effects
Jinrui Yang, Qing Liu, Yijun Li +5
Recent image generation models produce impressive composites, but often fail to preserve the identity of user-provided content when editing specific elements: the surrounding scene…
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Shilong Zhang, He Zhang, Zhifei Zhang +11
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To uni…
SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces
Sumit Chaturvedi, Mengwei Ren, Yannick Hold-Geoffroy +3
We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to chan…