stable-diffusion-webui

stable-diffusion-webui copied to clipboard

As I send every saved image to a discord channel, I don't want a grid for n_iter == 1 because it causes duplicates. Don't know if this code is clean...

orionaskatu

Small typo StableDiffuionModelHijack() => StableDiffusionModelHijack()

orionaskatu

img2img SD upscale gives out 512 output

2

I think SD upscaling is now limited to 1024 output,, would be nice to have options for higher res, even tho im not really sure if there will be a...

1blackbar

Buttons on UI to load previous /next image file from folder , in img2img tab and upscalers tab.

2

Its pretty overwhelming after awhile when we have thousands of generated images and we load one by one to upscale seeking for particular ones, So i think it would really...

1blackbar

https://heibox.uni-heidelberg.de/f/4d9ac7ea40c64582b7c9/?dl=1 taken from compvis repo for inpainting line: `wget -O models/ldm/inpainting_big/last.ckpt https://heibox.uni-heidelberg.de/f/4d9ac7ea40c64582b7c9/?dl=1`

pandoras-rabbithole

[Feature Request] SD upscale in txt2img mode

1

would be nice to have it in there as well. And even better - would be cool if we could automate the whole process. As in: first have the image...

lashmanRB

https://www.youtube.com/watch?v=N913hReVxMM I think it works pretty well but i wouldnt implement it like he did (on small 512 image and synthesizing whole image) What i would do is open a...

1blackbar

All is working well but i was wondering can you incorporate esrgan blending with original ? So we can move slider like with gfpgan and it would blend two images...

1blackbar

Implementation of Stable Diffusion with Aesthetic Gradients

25

here the original repo: https://github.com/vicgalle/stable-diffusion-aesthetic-gradients  

MalumaDev

Add hypernetwork settings to default quick setting list

4

Fixes #2490 & #2759

0xItx