DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models
PulseAugur coverage of DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models — every cluster mentioning DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Adaptive controller optimizes diffusion models for faster, high-quality image generation
Researchers have developed an adaptive controller for diffusion models that dynamically adjusts the number of denoising steps based on the complexity of text prompts. This method aims to improve the efficiency of text-t…
-
New DynEval framework offers holistic evaluation for text-to-image models
Researchers have introduced DynEval, a novel framework for holistically evaluating text-to-image (T2I) generative models. This framework addresses limitations of existing static evaluation methods by dynamically assessi…
-
New routing system optimizes text-to-image generation cost
Researchers have developed a cost-aware routing system for text-to-image generation that dynamically adjusts computational resources based on prompt complexity. This framework routes each prompt to the most suitable gen…