civitai VS lora

I find it quite funny, especially if you realize that something like 90% of the Stable Diffusion model fine-tunes out there are actually made for generating porn or images of females. Go to the website that has the most image generation models to verify this for yourself: https://civitai.com

WARNING don't visit this site on your work computer.

Remember The Website Obesity Crisis [1] article from 2015, since then [2] things only got worse, and it is been almost 10 years already (at the end of 2024).

Is it foolish to say that in 10 more years you wont be able to navigate the web on a circa 2015 PC ? If nothing changes seems like it.

My old macbook from 2013 with latest Firefox is already can not handle loading https://civitai.com web page with 23.98 MB of JavaScript, it is just hangs for half a minute while trying to render this disaster of web frontend.

[1] https://idlewords.com/talks/website_obesity.htm

[2] https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

One of the most popular free AI image generators right now is Civitai. Civitai uses a cutting-edge AI model to turn text prompts into photorealistic images in seconds.

Soz, I don't like to cross link my accounts, especially with all this TSWift shenanigans going around. But, if you look at https://civitai.com/ plenty of people have links to their ko-fi accounts where you can commission them (heck you may even find me somewhere on there).

civitai.com ?

all the samples images on models at https://civitai.com/ have prompts included. I used to have a bunch of sites that list prompts bookmarked, but I lost all my bookmarks recently :(

https://civitai.com/ most people grab models here these days I think. At least I do. And yeah, make sure to put checkpoints in the model folder, and lora in the lora folder, and hit the refresh button and it should show up.

Go to civitai.com, look for images that look realistic, study their prompts and the models used to generate them.

Tons of models to pick from on Civitai. I have a bunch downloaded for making NPCs for DnD.

Diffusion unet has an "extended" version nowadays that applies to the resnet part as well as the cross-attention: https://github.com/cloneofsimo/lora

Absolutely. But that doesn't matter because you only have to train it at scale, once. There are papers released already that show it's possible to update weights in small sections. You won't have to wait for the next monolithic LLM to drop to get up to date information. It will start to learn in bits and pieces.

No, it's a deep learning thing

Low Rank Adaptation of Large Language Models.

Recently, I have seen the LoRA technique (Low-Rank Adaptation of Large Language Models) as a popular method for fine-tuning LLMs and other models.

Enter LoRA, a method proposed for adapting pre-trained models to specific tasks[2]. By freezing pre-trained model weights and injecting trainable rank decomposition matrices into the transformer architecture, LoRA can reduce the number of trainable parameters and the GPU memory requirement, making the adaptation of LLMs for downstream tasks more feasible.

Open-source LLM projects have largely solved this using Low-Rank Adaptation of Large Language Models (LoRA): https://arxiv.org/abs/2106.09685

Apparently an RTX 4090 running overnight is sufficient to produce a fine-tuned model that can spit out new Harry Potter stories, or whatever...

Alpaca was trained for $600 ($100 for the smaller model) and offers outputs competitive with ChatGTP. https://arxiv.org/abs/2106.09685