stable-diffusion-krita-plugin VS taesd

> or maybe it was just this shared in earlier form). https://github.com/sddebz/stable-diffusion-krita-plugin

Nah that is an early version of a plugin that uses A1111 as the backend instead of ComfyUI (it does have a newer and maintained replacement, but its not the one in OP, which uses a ComfyUI backend.)

There are plugins for Gimp and Krita.

Yeah I've found two actually, I haven't tried either of them yet though so I have no idea how well they work https://www.youtube.com/watch?v=nP8MuRwcDN8 https://github.com/sddebz/stable-diffusion-krita-plugin

Krita Plugin : https://github.com/sddebz/stable-diffusion-krita-plugin

Thanks for the writeup. I've been doing something similar, but directly in Krita (free, open source drawing app) using this SD Krita plugin (based off the automatic1111 repo).

Neat! Does this have any relation to https://github.com/sddebz/stable-diffusion-krita-plugin?

Currenlty VAE decoding is 25% of the time spend rendering once the models are loaded. You can get faster result by not decoding the latent using a vae and instead using the preview, if you have TAESD ( https://github.com/madebyollin/taesd ) installed these previews are quite good. In theory a custom latent input to image output node using TAESD could be a massive speed increase compared to the usual vae decode.