Keith Kjer's starred repositories
InvokeAI
InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
sd-webui-controlnet
WebUI extension for ControlNet
latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
fast-stable-diffusion
fast-stable-diffusion + DreamBooth
k-diffusion
Karras et al. (2022) diffusion models for PyTorch
hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
projected-gan
[NeurIPS'21] Projected GANs Converge Faster
denoising-diffusion-gan
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804
LIVE-Layerwise-Image-Vectorization
[CVPR 2022 Oral] Towards Layer-wise Image Vectorization
vision-aided-gan
Ensembling Off-the-shelf Models for GAN Training (CVPR 2022 Oral)
bizarre-pose-estimator
WACV2022: Transfer Learning for Pose Estimation of Illustrated Characters
stylegan2ada
StyleGAN2-ada for practice
DiscoDiffusion4.1forAWSStudioLab
DiscoDiffusion 4.1 for AWS StudioLab