4 papers
Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion
Jiwon Kim, Pureum Kim, SeonHwa Kim +3
Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring…
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
Donghoon Ahn, Hyoungwon Cho, Jaewon Min +6
Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as cl…
Identity-preserving Distillation Sampling by Fixed-Point Iterator
SeonHwa Kim, Jiwon Kim, Soobin Park +5
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions…
A Noise is Worth Diffusion Guidance
Donghoon Ahn, Jiwon Kang, Sanghyun Lee +9
Diffusion models excel in generating high-quality images. However, current diffusion models struggle to produce reliable images without guidance methods, such as classifier-free gu…