SD3-Medium
PulseAugur coverage of SD3-Medium — every cluster mentioning SD3-Medium across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New ReSeed method restores diversity in distilled diffusion models
Researchers have developed a new method called ReSeed to improve the diversity of images generated by distilled diffusion models. They found that the first denoising step is crucial for maintaining diversity, as distill…
-
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-…
-
New method StraightDP enhances differential privacy for generative models
Researchers have developed StraightDP, a novel method for differentially private training of text-conditioned generative models. This approach addresses the utility cliff often encountered with strong privacy settings b…
-
China develops JuZhou 1.0, an edge-native text-to-image model trained on domestic AI accelerators
Researchers have developed JuZhou 1.0, a novel, lightweight text-to-image foundation model designed for efficient on-device execution. This model achieves its compact size and speed through a small parameter count, effi…
-
New Linear-DPO method improves text-to-image model alignment
Researchers have introduced Linear-DPO, a novel method for aligning text-to-image generative models. This approach generalizes the Direct Preference Optimization objective to encompass both diffusion and flow-matching m…
-
New CDM method enhances diffusion model distillation for faster, higher-fidelity image generation
Researchers have introduced Continuous-Time Distribution Matching (CDM), a novel method for accelerating diffusion models. This approach moves beyond discrete-time distillation by employing a dynamic, continuous schedul…