6 papers · 1 filter
Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models
Artem Sergievskii, Artyom Turevich, Sergey Kastryulin
Inference-time quality-enhancement methods are an effective and widely adopted means of improving diffusion models without expensive retraining. We study a family of training-free…
DuET: Dual Expert Trajectories for Diffusion Image Editing
Lidia Troeshestova, Alexander Ustyuzhanin, Sergey Kastryulin
Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent source-image conditioning can limit…
Alchemist: Turning Public Text-to-Image Data into Generative Gold
Valerii Startsev, Alexander Ustyuzhanin, Alexey Kirillov +2
Pre-training equips text-to-image (T2I) models with broad world knowledge, but this alone is often insufficient to achieve high aesthetic quality and alignment. Consequently, super…
YaART: Yet Another ART Rendering Technology
Sergey Kastryulin, Artem Konev, Alexander Shishenya +20
In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study…
QUASAR: QUality and Aesthetics Scoring with Advanced Representations
Sergey Kastryulin, Denis Prokopenko, Artem Babenko +1
This paper introduces a new data-driven, non-parametric method for image quality and aesthetics assessment, surpassing existing approaches and requiring no prompt engineering or fi…
Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
Aleksandr Belov, Joel Stadelmann, Sergey Kastryulin +1
We went below the MRI acceleration factors (a.k.a., k-space undersampling) reported by all published papers that reference the original fastMRI challenge, and then considered power…