Replies: 1 comment 1 reply
-
I agree on that. And please, add the ability to generate images manually and/or automatically. Great Feature anyway! |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
There seems to now be a new way to browse for textual inversion embeddings and hyper networks etc!
However, the UI is super HUGE.
Maybe make it a text only list, or a list with rows that show a name and small thumbnail after it? Personally, I think something like txt2img sampler selection dropdown would be great (even without some preview), even better if it had search field so it would be possible to type "paint" and you would get all the embeddings with that substring.
Or at least make it like some sort of scroll list area if possible, instead of like now, one has to scroll 10 full screens if there are many embeddings :)
Maybe even use 1x1 images, as SD after all likes square images? Unless there is going to be some info in addition to preview images.
Also, the no preview image seems to be like something generated by SD :) make it have real text.
Beta Was this translation helpful? Give feedback.
All reactions