Optimal Control Meets Flow Matching: A Principled Route to Multi-Subject Fidelity Paper • 2510.02315 • Published Oct 2 • 5
RefAM: Attention Magnets for Zero-Shot Referral Segmentation Paper • 2509.22650 • Published Sep 26 • 4
Apertus LLM Collection Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 4 items • Updated Oct 1 • 306
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute Paper • 2502.20126 • Published Feb 27 • 20
UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency Paper • 2412.15216 • Published Dec 19, 2024 • 5
High-Fidelity Virtual Try-on with Large-Scale Unpaired Learning Paper • 2411.01593 • Published Nov 3, 2024 • 2
MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation Paper • 2411.04357 • Published Nov 7, 2024 • 1
LoRACLR: Contrastive Adaptation for Customization of Diffusion Models Paper • 2412.09622 • Published Dec 12, 2024 • 8
BRAVE: Broadening the visual encoding of vision-language models Paper • 2404.07204 • Published Apr 10, 2024 • 19
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models Paper • 2406.14599 • Published Jun 20, 2024 • 17
LIME: Localized Image Editing via Attention Regularization in Diffusion Models Paper • 2312.09256 • Published Dec 14, 2023 • 12