7/31/2023 0 Comments Krita for mac m1![]() Sometimes you strike gold and get lucky on your first generation - but that's rare. It's a semi-creative process and definitely takes some time investment if you want great results. That seed will likely generate more things in a similar style for similar enough prompts. Make variations of the variations you like best.Īlso the seed is very important! If you find a seed that generated a style you really liked take note of it. Play around with it! If you find an image that's very close to what you want - start generating variations of it. ![]() Try shuffling the order of your prompt - the order of the tokens does matter! Repeat a token twice, thrice, hell make a prompt with nothing but the same token repeated 8 times. I'd recommend keeping a prompt list and finding what does/doesn't work for what you're after. It's an iterative process and many of the fantastic images you see weren't "first generations" but likely the 20th or so generation after tons of trial and error working around a specific prompt/idea. That means knowing the right keywords to get specific styles or effects, a little bit of luck, and sometimes generating a prompt several dozen times and then creating variations from a seed once you find a specific seed that generated something close to what you liked. Half of generating something good is guiding the program into generating something good. When people call themselves "prompt engineers" it's only half in jest. I’m trying not to be harsh – I understand that this code is more of a code dump from researchers than a real software project, and they’ve done some incredibly clever things here – but if somebody is suggesting that Python projects in general are like this, it really should be pointed out that this is not in this slightest bit representative of a typical Python project. Put them on a team like that and they’ll be forced to unlearn most of these bad habits fast because they’d never get their pull requests approved otherwise. This is the kind of codebase you get when you have people who have been writing code for a long time, but never in the context of a software engineering project alongside experienced software engineers they can learn from. Like I said, they can write clever code, but there’s a difference between bashing on code until it works and building it properly. ![]() ![]() No, but it is a project made by people lacking software engineering skills, which is a distinction I drew in my earlier comment. > This is not a project made by people without dev skills. Unless it’s code released by researchers, etc. ![]() Not all Python software gets all of this right, but it’s incredibly rare to have so many misses, even for hobbyist developers. Why is there precisely one test (that has nothing to do with the core functionality)? Why is the Git history full of things like “finish”, “correct merg”, “fix more”, “add code”? Where is the linting config? Why are there print statements everywhere? Why does non-UI code have UI code embedded in it? Why is there random code commented out? Why is there no consistency across the codebase? Why is everything written as if they’ve never seen a Python project before (comments that should be docstrings, docstrings that should be comments, print("WARNING: ") instead of using logging or warnings, underscores in CLI flags, no shebangs in scripts intended to be run from the command line…) Really? I find the difference between the Stable Diffusion code and the code you find in a typical Python package to be night and day. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |