Papers4

All Beginner Intermediate Advanced

All Sources arXiv

#SDXL

Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

Intermediate

Euisoo Jung, Byunghyun Kim et al.Feb 25arXiv

Diffusion models make great images but are slow because they fix noise step by step many times.

#diffusion inference#multi-GPU acceleration#data parallelism

Optimizing Few-Step Generation with Adaptive Matching Distillation

Intermediate

Lichen Bai, Zikai Zhou et al.Feb 7arXiv

Diffusion models make great images and videos but are slow because they usually need many tiny steps.

#diffusion distillation#few-step generation#distribution matching distillation

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Intermediate

Tianhe Wu, Ruibin Li et al.Feb 3arXiv

The paper solves a big problem in fast image generators: they got quick, but they lost variety and kept making similar pictures.

#diffusion distillation#distribution matching distillation#mode collapse

Alterbute: Editing Intrinsic Attributes of Objects in Images

Intermediate

Tal Reiss, Daniel Winter et al.Jan 15arXiv

Alterbute is a diffusion-based method that changes an object's intrinsic attributes (color, texture, material, shape) in a photo while keeping the object's identity and the scene intact.

#intrinsic attribute editing#visual named entities#identity preservation