OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-04-25 06:19:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated Features (markdown)

AUTOMATIC1111 2022-09-30 16:57:10 +03:00
parent f8256379f5
commit 6b2d8bd78d
1 changed files with 4 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
Features.md

@ -159,23 +159,13 @@ Here's are settings that create the graph above:
![](images/xy_grid-medusa-ui.png) ![](images/xy_grid-medusa-ui.png)
# Textual Inversion # Textual Inversion
Allows you to use pretrained textual inversion embeddings. See original site for details about what textual inversion is: https://textual-inversion.github.io/.
See original site for details: https://textual-inversion.github.io/.
I used lstein's repo for training embdedding: https://github.com/lstein/stable-diffusion; if
you want to train your own, I recommend following the guide on his site.
Update: you can now download many pre-trained embeddings from this page: https://huggingface.co/sd-concepts-library Short explanation: place your embeddings into `embeddings` directory, and use the filename in prompt.
To make use of pretrained embeddings, create `embeddings` directory in the same directory as `webui.py` Long explanation: [Textual Inversion](Textual-Inversion)
and put your embeddings into it. They must be .pt or .bin files about 5Kb in size, each with only
one trained embedding, and the filename (without .pt or .bin) will be the term you'd use in prompt
to get that embedding.
As an example, I trained one for about 5000 steps: https://files.catbox.moe/e2ui6r.pt; it does ![grid-0037](https://user-images.githubusercontent.com/20920490/193285770-9454c5e1-e594-463c-8be8-1488ddf2877b.png)
not produce very good results, but it does work. Download and rename it to `Usada Pekora.pt`,
and put it into `embeddings` dir and use Usada Pekora in prompt.
![](images/inversion.png)
# Resizing # Resizing
There are three options for resizing input images in img2img mode: There are three options for resizing input images in img2img mode: