Here you find the vector data that you would need if you like to play with my latest baby.
It is called Prompt Quill and it will help you make nice prompts more easy. Its not just a dull Prompt helper you might know, it is the world's first RAG workflow feeded with more than 4.9 Million Prompts I did take from Civitai and other sources with their permission.
The data is now prepared to deliver negative prompts as well as models that might work well with the generated prompt. Also there is a one click installer to all versions, also all versions now support image generation with the created prompts, so its really getting time you start trying it =)
Find the sources you need here: https://github.com/osi1880vr/prompt_quill
If you like it please leave a thumbs up =)
You like to contribute, just raise an PR on github.
There is new features, it now allows for a deep dive into the context aka found prompts from the vector store, you can run batches of prompt generation and you can enter your prompt in your native language, it will then get translated into english and processed from there, the translated prompt will also be shown in the output so you can have an idea what it translated to.
You like to get in contact PM me here or find me on discord: https://discord.gg/Krn9UutdGH
One last thing, I'm very interested to get this thing to life on some server, if you interested in sponsoring a long term hosting solution please lets talk :)
Description
The data contains now >4.9M Prompts
FAQ
Comments (11)
I am trying to install Prompt Quill as I write, but when it comes to the point of downloading the civital model it stops downloading at 8.386gb of data the starts another attempt. I am on my third attempt now with the same results.
Thats strange but pointing to a connection issue which is out of my control. you could try to use the download cache but I think it will hit the same roadblock.
I have the same problem as you. Always stuck at 10.2gb of data.
@AntiLeecher thats really strange, I did try it many many times to reproduce this issue but it always works for me, I know its the lame "its working on my box" excuse, but how I will find an error if I can not reproduce it. The downloader is doing 5 atemts to get the download done so if it fails at the same stage all the time the script did try 5 times to get the download working
Somehow I manage to pass it after like 20 times. Lol. But it seems still using Data v2, how to update to v3?
the installation is interrupted because the download is cut, the same thing happens every time I try and apparently it has happened to other people, I tried to download the model from Civitai and put it manually and connection errors occur here in Civitai itself, could not you try to correct the installation to install the ‘model data’ from Huggingface?
with every update here at Civitai one thing is fixed and another is broken.
it's a pity that this tool is tied to be installed with civitai because it depends more on the stability of this site, I will try this tool later when they fix this problem because it seems to be very useful! greetings and keep up the good work!!!
I get that a lot, I fail to reporduce it to be able to fix the issue. In the docus folder you should find a manual install instruction, maybe that can help. I'am very sorry for the complex istall issues. it is quite a beast with loads of dependencies.
@osi1880vr I will try the manual installation when I have a lot of time someday, they are too many steps that few would be willing to go through because the result may be useless, since there are no guarantees or testimonials from anyone that it is useful to go that way, but yourself as the creator.
there are some ways to solve this problem but I don't know if they are possible:
1. install the repertoire without the need of any model and leave the interface ready to introduce models downloaded independently, like in Stable diffusion.
2. Compress the installation into an executable file, like Kobold does:
https://github.com/LostRuins/koboldcpp/releases
3. Modify the file "one_click_install" to download a small model, for example one of 2gb, because Civitai has problems with large files, so the installation is interrupted, the reason why this does not happen to you may be because of the cookies of the site.
4. Use Huggingface as an installation repository, Stable diffusion relies heavily on this and does not present errors.
Well for the moment these would be some ways to solve this, if I come up with another solution I will write it here
Compress it into an executable would be funny :D it will be like a 19GB executable :D
@osi1880vr actually the executable file that Kobold uses only incorporates the necessary instances for a quick installation without problems, from there, the program interface allows to incorporate LLM models from 4gb onwards in its quantized versions, I have even seen models with more than 19GB.
Try to download Kobold and see what models are there, I leave this link just in case of a user who uploads models heavier than 19GB:
https://huggingface.co/Lewdiculous
I hope you can find some way to solve the problem with your tool, I will come here from time to time to see if things are solved, greetings.
The problem is not on my side.
[ ] I have no idea what prompt quill is about
[ ] I have no idea what im talking about at all
take your poison :P


