Version 2: Multibench benchmark, concept specific and all-in-one finetuning, Canny edge (P-T2I) benchmark
@article{patel2024lambda, title={λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space}, author={Patel, Maitreya and Jung, Sangmin and Baral, Chitta and Yang, Yezhou}, journal={arXiv preprint arXiv:2402.05195}, year={2024} }
Weight Modulation for User Attribution and Fingerprinting in T2I Models.
Evaluating Concept Learning Abilities of T2I Models