Suggestion/Request

[LumberingTroll]

First, thank you so much for making this!

1. If possible it would be amazing to be able to add custom tags to our TI, Ckp, Lora, HN, etc. so that I could say add a "Character" tag to all my character/person based Lora and easily find them, same for Styles, Helpers, Negatives, Utilities, etc.!

2. The ability to store a note that we could put in our trigger words and used prompts for quick reference on each of these it would save a lot of moving between documents / sites and looking up stuff making the entire workflow faster.

3. Download updated models/lora/embeddings without having to manually go to the site to download them, and also the option to delete old models automatically.

4. NSFW toggle on the main WebUI that will filter out all NSFW when its on. (some times I want to show people things, but dont want those visible, my kinks are my own :P )

Again I really appreciate your efforts and if these requests are not possible I understand.

[butaixianran]

This is a Civitai extension, not a everything extension.

Local model and image management is not a Civitai feature. They should be done in another extension.

But, about your first request, you can create subfolders in your model folder, then put different model in different subfolder.

Like one for cartoon, one for photoreal. This is an extra network's buildin feature

[LumberingTroll]

This is a Civitai extension, not a everything extension.

Local model and image management is not a Civitai feature. They should be done in another extension.

But, about your first request, you can create subfolders in your model folder, then put different model in different subfolder.

Like one for cartoon, one for photoreal. This is an extra network's buildin feature

Thanks for the info!

[MrKuenning]

I am also hoping for something like that.
There have been two other similar requests on this extension:

#18

#26

With user @jokker87 saying he would develop an extension like that soon.

There is also a pull request on the official web ui that I commented a similar request on.

AUTOMATIC1111/stable-diffusion-webui#8366

MrKuenning Wrote:

What I would love to see is an extension that creates a metadata file next to each model.

That we could store the:

• Title
• Description
• Recommended Weight
• Trigger Phrase - prompt to go with the model
• URL
• Maybe? Example Prompt

Then when you mouse over the model you would see a description. Clicking on the model would put not only the model tag, but also the recommended weight value and the trigger phrase.

For example, if I clicked on a Mazda Miata LoRA, rather than just adding <lora:Mazda Miata:1> to the prompt,

it would put <lora:Mazda Miata:0.6>, MazdaMiata, 1car

The metadata files should be universal, such as JSON or XML. Easy to edit manually. But there should also be an edit icon in the UI on the model to edit the fields.

Additionally, it would be nice to have it scrape starting metadata from sites like Civitai to pull the initial values, which could then be modified.

I find the default weight of 1 and recommended trigger words are almost never enough on their own to get a good result. I have been manually adding every single LoRA, TI, and Hyper to my Styles CSV list to have it fill in the best weight, and trigger phrase combo. This works, but is annoying as it requires me to double my efforts. It would be great to be able to specify the values that I want for each model.

[jokker87]

@MrKuenning Here's a first somehow working version with that feature. I tried to implement it in the base code of this extension, so that you get the best of both ;)

https://github.com/jokker87/Stable-Diffusion-Webui-Civitai-Helper

[Blackened15]

Dont wanna create another "issue" thread for a suggestion.

A "Use SFW images on mixed/NSFW model when possible" or something like that would be useful, so it default to using safe for work image preview on model that have both type of image, but still use an NSFW image when thats all thats available.

Also thanks for the extention, saving me hours of work!

Right now I achieve this by scanning without the skip NSFW Preview Image, manually going through the mixed model, deleting the preview and info, and rerunning with the skip option, so it downloads the SFW image on those, while still generating preview on NSFW model

[butaixianran]

Check this new extension:
https://github.com/butaixianran/sdweb-easy-prompt-selector

[Blackened15]

dont know if that reply was meant to me or in general, but I just wanted to clarify and simplify my suggestion.

An "Skip NSFW Preview images when possible" option would be great, meaning it would use SFW preview picture when possible, but fall back on NSFW if there is no SFW possibilities

[butaixianran]

dont know if that reply was meant to me or in general, but I just wanted to clarify and simplify my suggestion.

Above new extension is not for your request. There will be no more new feature in v1.x as document says. Your above request will be added to 2.0

[Blackened15]

cool, great work so far

[LumberingTroll]

Check this new extension: https://github.com/butaixianran/sdweb-easy-prompt-selector

Thats awesome! thanks a lot!