OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-02-12 00:22:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated Textual Inversion (markdown)

AUTOMATIC1111 2022-10-13 18:43:31 +03:00
parent e50423426b
commit bc329c9fea
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Textual-Inversion.md

@ -105,5 +105,8 @@ Training works the same way as with textual inversion.
The only requirement is to use a very, very low learning rate, something like 0.000005 or 0.0000005. The only requirement is to use a very, very low learning rate, something like 0.000005 or 0.0000005.
## Unload VAE and CLIP from VRAM when training ### Dum Dum Guide
An anonymous user has written a guide with pictures for using hypernetworks: https://rentry.org/hypernetwork4dumdums
### Unload VAE and CLIP from VRAM when training
This option on settings tab allows you to save some memoryat the cost of slower preview picture generation. This option on settings tab allows you to save some memoryat the cost of slower preview picture generation.