Stable Diffusion ControlNet Explained | Control Net Examples

ControlNet is a neural network structure to control diffusion models by adding extra conditions. It copies the weights of neural network blocks into a "locked" copy and a "trainable" copy. The "trainable" one learns your condition. The "locked" one preserves your model. Thanks to this, training with small dataset of image pairs will not destroy the production-ready diffusion models. References: ControlNet Github Repo - https://github.com/lllyasviel/ControlNet ControlNet Growth https://twitter.com/ClementDelangue/status/1630259781742067718 ControlNet Models - https://huggingface.co/models?sort=likes&search=control MagicPose https://twitter.com/Yamkaz/status/1626486302962245633 ControlNet Edge (Logo Landscape) - https://twitter.com/skirano/status/1630360159808634880 MultiControlNet - https://twitter.com/bilawalsidhu/status/1629632110456602631 ControlNet Consistent Images - https://twitter.com/Toby_Frank/status/1629912421849767941/photo/3 ControlNet Dreambooth - https://twitter.com/dannypostmaa/status/1630442372206133248