idkman

I was in the same circumstances when I started. But then I asked around which helped me properly configure it.

Umm... Yeah I'm not so sure. Check the prompt in the screenshot image. Although detailed, but ain't exactly optimised for sd prompts.

Would prefer to use LLM in a manner of guiding or inspiring, but won't crucially depend on an LLM to create prompts.

In excitement of trying out stable cascade I installed it but went out of memory. Damn!

Cool! I'll keep making new pages as I come across new stuff!

I've signed up on the wiki. How do I start?

this list helped me get started with SD. Looking back it at now, I think it needs to be updated. How can I contribute?

I had a really hard time installing the tensorRT extension for 1111

Nvm, https://www.kaggle.com/code/timothyalexisvass/latent-space-experiments

Has someone implemented this? I want to try out this shift

What I dislike about lower quantization is quality degradation. In my small experience, i find 7b models dumb (I've only tested Q4KM GGUF), and needed to be provided proper context before moving forward with the constructive conversation (be chat or instruct).

If this issue can be circumvented in lower quantization, I'm all in.

In context of SD, going below fp16 would only make things faster at cost of quality, and I personally like to go in depth with my prompts. For simpler prompts sure, even lighting and turbo are good in that regard.

Haha no. I mean in the context of providing in control, DPO does a better job than FreeU.

https://www.youtube.com/watch?v=mrKk0yYUdnU

The paper mentions it manipulates main net features(B) and skip features(S).

Not sure what the main net features are, but I'm assuming skip features are like clip skip?

Although the paper mentions S didn't do anything, in my tests (sdxl base), it had a tremendous amount of adverse effect on the image generated.

TBH, i enjoy using DPO more than freeU, but I'm curious to learn.