IEEE

Enhancing Semantic Segmentation with Synthetic Image Generation: A Novel Approach Using Stable Diffusion and ControlNet

Abstract: This paper presents a novel methodology for generating synthetic images that adhere accurately to provided semantic segmentation maps using the Stable Diffusion model with the ControlNet ...
Hosted on MSN

Photoshop tutorial: How to add a star-diffusion effect to photographs

Photoshop cc tutorial showing how to add a romantic, star-diffusion (twinkle) effect to your photos and then confine the effect to specific areas. Grocery stores are about to get worse What the US ...
IEEE

SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering

Abstract: Data synthesis and augmentation are essential for Sound Event Detection (SED) due to the scarcity of temporally labeled data. While augmentation methods like SpecAugment and Mix-up can ...
GitHub

Diffusion Transformers with Representation Autoencoders (RAE)

We present Representation Autoencoders (RAE), a class of autoencoders that utilize pretrained, frozen representation encoders such as DINOv2 and SigLIP2 as encoders with trained ViT decoders. RAE can ...
GitHub

Cascade Inpainting Model (LaMa+SD1.5)

Custom image inpaint model based on Stable Diffusion 1.5, developed to remove, edit or reconstruct specific regions of an image by leveraging conditioning with textual prompts and Canny edges, with ...