This is also friendly to merge/replacement/offsetting of models/weights/blocks/layers. This allows training on small-scale or even personal devices. The "zero convolution" is 1×1 convolution with both weight and bias initialized as zeros.īefore training, all zero convolutions output zeros, and ControlNet will not cause any distortion. Thanks to this, training with small dataset of image pairs will not destroy the production-ready diffusion models. The "trainable" one learns your condition. It copys the weights of neural network blocks into a "locked" copy and a "trainable" copy. Official implementation of Adding Conditional Control to Text-to-Image Diffusion Models.ĬontrolNet is a neural network structure to control diffusion models by adding extra conditions. Those new models will be merged to this repo after we make sure that everything is good. News: A nightly version of ControlNet 1.1 is released!ĬontrolNet 1.1 is released.
0 kommentar(er)
