Muhammad Rizqi Nur

I may be able to work on it, but I'm new to this so only simple builtin components, no previews. There are issues though AFAIK gradio only supports multiple selection...

Okay I was trying to make it, well, sort of, it's actually [a blacklist](https://github.com/R-N/stable-diffusion-webui/tree/embedding-select) instead. Anyway I found out that embeddings are loaded and used by their filename instead of...

Found out that the None option is still bugged in #3986 . Will PR fix later with other stuff

> You won't typically suffer much from exploding gradients after the model is stable and it's just fine-tuning, unless the lr is absurdly large. I don't think it will change...

> How much more effective will the training be with textual embedding? Is it faster to reach the goal or is it able to bring out more detail and interpretation?...

> You can read more about the hypernetwork in the blog (https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac), but don't consider them a new model, it's only a new module (in the Pytorch concept of module)...

I haven't experimented further. I've simplified it, if I get what you meant correctly.

> For my personal interest, is there any fair comparison between VAEs ? I couldn't find any through google nor in this repository's issues or discussions. Thanks in advance. [This](https://huggingface.co/stabilityai/sd-vae-ft-mse-original)...

> The refresh button spans across a large chunk of the quick settings bar. Pic below.  > ... Yeah it seemed a bit longer on my screenshot too but...

Also I'll try to improve the loading (issue 1) later when I have the time, maybe in few days (or this can just get merged and I'll make another pull...