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 - github.com/lll...
ControlNet Growth / 1630259781742067718
ControlNet Models - huggingface.co...
MagicPose / 1626486302962245633
ControlNet Edge (Logo Landscape) - / 1630360159808634880
MultiControlNet - / 1629632110456602631
ControlNet Consistent Images - / 3
ControlNet Dreambooth - / 1630442372206133248
Негізгі бет Stable Diffusion ControlNet Explained | Control Net Examples
Пікірлер: 37