PixArt-alpha
PulseAugur coverage of PixArt-alpha — every cluster mentioning PixArt-alpha across labs, papers, and developer communities, ranked by signal.
-
RegionCache speeds up multi-turn image editing by reusing diffusion states
Researchers have developed RegionCache, a new framework designed to improve the efficiency of multi-turn image editing using diffusion transformers. This method intelligently reuses diffusion states from unchanged regio…
-
New method recalibrates Diffusion Transformers for analog compute-in-memory hardware
Researchers have developed a novel method to recalibrate Diffusion Transformers (DiTs) when used with analog compute-in-memory (CIM) hardware. This approach addresses how CIM's inherent nonidealities distort the classif…
-
New research offers advanced control and safety for text-to-image AI
Two new research papers propose novel methods for enhancing control and safety in text-to-image generation models. The first, DiSCO, offers a black-box defense against generating Not-Safe-For-Work (NSFW) content by opti…
-
New research explores diffusion models, bias mitigation, and reinforcement learning applications · 10 sources tracked
Recent research explores advancements in diffusion models, focusing on theoretical underpinnings, optimization techniques, and bias mitigation. One paper introduces Bayesian Information Restricted Diffusion (BIRD) model…
-
DataEvolver framework improves text-rich image generation data construction
Researchers have developed DataEvolver, a novel multi-agent framework designed to enhance the creation of training data for text-rich image generation. This system utilizes feedback from rejected image samples to iterat…