Pixart
PulseAugur coverage of Pixart — every cluster mentioning Pixart across labs, papers, and developer communities, ranked by signal.
-
DICE technique enhances text-to-image generation by refining embeddings
Researchers have developed a new technique called DICE (Distilling Classifier-Free Guidance into Text Embeddings) to improve text-to-image generation. DICE refines text embeddings to mimic the effects of classifier-free…
-
New methods accelerate Diffusion Transformers for faster image generation · 2 papers
Two new research papers propose methods to accelerate Diffusion Transformers (DiTs), which are computationally intensive for high-resolution image and video generation. The first paper, Shiva-DiT, introduces a residual-…
-
Diffusion models research tackles outliers, efficiency, and theory · 10 sources tracked
Recent research explores advancements in diffusion models, focusing on improving their robustness, efficiency, and theoretical understanding. Papers address challenges like outlier data in inverse problems, scaling rein…
-
New methods accelerate diffusion models with novel feature caching strategies · 2 sources tracked
Two new research papers propose novel methods to accelerate diffusion models, which are computationally intensive for image and video generation. The first paper, "Rethinking Token-wise Feature Caching," introduces DuCa…
-
14 image generation models compared for fine-arts media rendering
A user has developed a custom tool to evaluate how 14 different image generation models render fine-arts media. The tool utilizes slightly modified ComfyUI workflow templates and a set of style prompts to create overvie…