view article Article Introducing AuraFace: Open-Source Face Recognition and Identity Preservation Models By isidentical • Aug 26 • 36
AuraFlow Collection AuraFlow v0.x series, to date the largest (6.8B) and highest fidelity (0.7+ on GenEval) open sourced text to image model. • 3 items • Updated Sep 6 • 5
AuraSR Collection Fastest super resolution model for AI generated images • 2 items • Updated Jul 30 • 2
Compositional Text-to-Image Generation with Dense Blob Representations Paper • 2405.08246 • Published May 14 • 12
Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning Paper • 2405.08054 • Published May 13 • 21
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory Paper • 2405.08707 • Published May 14 • 27
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model Paper • 2405.09215 • Published May 15 • 18
CAT3D: Create Anything in 3D with Multi-View Diffusion Models Paper • 2405.10314 • Published May 16 • 44
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm Paper • 2403.11781 • Published Mar 18 • 17
IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models Paper • 2403.13535 • Published Mar 20 • 22
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation Paper • 2403.04692 • Published Mar 7 • 40
Inst-Inpaint: Instructing to Remove Objects with Diffusion Models Paper • 2304.03246 • Published Apr 6, 2023 • 2