Like lots of other people, I've been playing around with AI generated art (text to image). In my case, I've been using Stable Diffusion UI which is an easy to install variant of Stable Diffusion that also includes a graphical user interface. I was able to get it running on both Windows and Linux without much effort. While the included GUI is nice, the easy install was what appealed to me the most. Not all packages are so friendly.
To get fast results you need a decent GPU with lots of VRAM onboard. However, you don't need a GPU to use Stable Diffusion UI as long as you have patience. If you don't have or use a GPU and use only the CPU, each image will take a long time to produce. It can take thirty minutes or more depending on your CPU speed and the settings you use. However, this is open source software so you can generate as many images as you want for free. The end result is that even with limited hardware, you can still produce unlimited images as long as you are patient.
They cyborg images I have been generating have different prompts but all of them have either the word 'cyborg' and/or the words 'cybernetically enhanced'. The rest of the words are just further description that I vary somewhat between groups of images.
Including "cybernetically enhanced" in the prompt usually makes the images look disturbing or downright malevolent. This one is too. This is also the second one that could be considered NSFW. Don't fall for it though, the AI is doing this just to distract you...
Thank you, friend!
I'm @steem.history, who is steem witness.
Thank you for witnessvoting for me.
please click it!
(Go to https://steemit.com/~witnesses and type fbslo at the bottom of the page)
The weight is reduced because of the lack of Voting Power. If you vote for me as a witness, you can get my little vote.
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit