I found a new high speed ai chatbot on the internet called PI that is free. It has only hallucinated once when I asked how to turn on dark mode. It is censored but does a great job at rewriting stable diffusion text prompts. You can try it out a few times before they make you register to continue. If you register it will remember your previous chat conversations:
I found a stable diffusion lightning model available on the web that generates an image in less than a second, as you type. It has been down a couple days now, not sure why. They say they will be back.
[Stable diffusion 3](https://stability.ai/news/stable-diffusion-3) is in alpha. It looks like it will be amazing when it is fully released any day now. It has features that blow away everyone else for getting the results you want.
There is a two minute paper on it.
I have switched over to using SDXL Lightning models from civitai. There are several good ones. They can give a great image in 4 steps that are 1024x1024 in size. They do require you to also change the cfg scale down to between 1 and 2. And it is a little picky on the sampler you use, so if you get a bad result punt down to euler and try a few different ones.
Olivio can tell you all about it.
No comments:
Post a Comment