News for hackers. Stuff that matters.
Re:A Web UI for Stable Diffusion by schleck8 on Friday September 09, 2022 @06:26PM (#32785642)
Those are prompt engineering keywords. SD is way more reliant on tinkering with the prompt than midjourney

https://moritz.pm/posts/parameters

Re:A Web UI for Stable Diffusion by throwaway1851 on Friday September 09, 2022 @08:05PM (#32786358)
MidJourney needs a lot of prompt engineering too. And Dall-E also. If you look at the prompt as an opportunity to describe what you want to see, the results are often disappointing. It works better to think backwards about how the model was trained, and what sorts of web caption words it likely saw in training examples that used the sorts of features you’re hoping it will generate. This is more of a process of learning to ask the model to produce things it’s able to produce, using its special image language.