2 papers
cs.CV2026
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…
cs.CV2025
IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models
Khaled Abud, Sergey Lavrushkin, Alexey Kirillov +1
Diffusion-based models have recently revolutionized image generation, achieving unprecedented levels of fidelity. However, consistent generation of high-quality images remains chal…