5 papers
ATATA: One Algorithm to Align Them All
Boyi Pang, Savva Ignatyev, Vladimir Ippolitov +8
We suggest a new multi-modal algorithm for joint inference of paired structurally aligned samples with Rectified Flow models. While some existing methods propose a codependent gene…
ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models
Dmitrii Sorokin, Maksim Nakhodnov, Andrey Kuznetsov +1
Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tu…
DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
Shamil Ayupov, Maksim Nakhodnov, Anastasia Yaschenko +2
Personalized diffusion models have shown remarkable success in Text-to-Image (T2I) generation by enabling the injection of user-defined concepts into diverse contexts. However, bal…
Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation
Vera Soboleva, Maksim Nakhodnov, Aibek Alanov
Personalized text-to-image generation aims to create images tailored to user-defined concepts and textual descriptions. Balancing the fidelity of the learned concept with its abili…
StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation
Aibek Alanov, Vadim Titov, Maksim Nakhodnov +1
Domain adaptation of GANs is a problem of fine-tuning GAN models pretrained on a large dataset (e.g. StyleGAN) to a specific domain with few samples (e.g. painting faces, sketches,…