8 papers
Learning in Curved Weight Space:Exponential-Linear Weight Reparameterization for Improved Optimization
Ethan Smith
Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances wh…
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
Xingjian Leng, Jaskirat Singh, Zhanhao Liang +5
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and rel…
MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale
Zhicong Tang, Zhao Zhang, Jingye Chen +6
Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editin…
NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches
Ethan Smith
We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an architectural augmentation that adds nonlinear low-rank branches to transformer linear layers. Unlike LoRA…
From Tokens to Numbers: Continuous Number Modeling for SVG Generation
Michael Ogezi, Martin Bell, Freda Shi +1
For certain image generation tasks, vector graphics such as Scalable Vector Graphics (SVGs) offer clear benefits such as increased flexibility, size efficiency, and editing ease, b…
LoRA Diffusion: Zero-Shot LoRA Synthesis for Diffusion Model Personalization
Ethan Smith, Rami Seid, Alberto Hojel +2
Low-Rank Adaptation (LoRA) and other parameter-efficient fine-tuning (PEFT) methods provide low-memory, storage-efficient solutions for personalizing text-to-image models. However,…
EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance
Zicheng Duan, Yuxuan Ding, Chenhui Gou +3
Zero-shot personalized image generation models aim to produce images that align with both a given text prompt and subject image, requiring the model to incorporate both sources of…
ToDo: Token Downsampling for Efficient Generation of High-Resolution Images
Ethan Smith, Nayan Saxena, Aninda Saha
Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time…