Latest info about Veronika Zemanová
In light of the latest Flux AI developments and the plethora of AI creations featuring Veronika which have already been created, a new section to the website has been added which features just the AI sets.
Here’s a link to the Set selection page: AI Sets.
Flux is a new AI image generation model developed by Black Forest Labs. It represents a significant advancement in AI-generated art, utilizing a “hybrid architecture” that combines transformer and diffusion techniques, scaled up to 12 billion parameters. To date all images had been using a standard Stable Diffusion model which due it’s inherent nature limited the size and quality of the generated images.
FLUX.1 [dev] is the latest version for non-commercial use. Recently a user on CivitAI generated a Veronika LORA which is by far the most accurate representation of Veronika. We recently had a chance to try it out and the results are to say the least absolutely remarkable. Images now really capture the true essence of Veronika.
Here are a few examples …. I hope you agree!!!!
With the improvements in AI generated art over the course of the last few years, ScottyJX has decided to create “simulated photo shoots” featuring Veronika. He has released about 2 new sets / week over the past few months. A sampling of some of the sets appear in the images below with most sets featuring between 40-160 AI generated images
To access the new material simply go to Actiongirls and subscribe!!!!
I was introduced to the power of Stable Diffusion a few weeks ago when I saw works of art literally created out of thin air by simply “describing” what you wanted the content of the image to contain. I explored the power of this a little more and discovered that it was also able to create a likeness of anyone through the use of “embeddings” where you produce a file containing the necessary parameters needed to steer the Stable Diffusion algorithm in the direction to the desired subject. This got me thinking …. oh … we can get Veronika out retirement and create a “metaverse” version. I searching around, I had found that someone on one of the AI forums had already created a basic Veronika model I could start with. After about 1.5 hours of loading the Stable Diffusion AI software on my server and then about another 2 days of playing around with settings, I was able to come up with these 2 almost photo realistic “new” AI created pictures of Veronika:
The resemblance if almost perfect. Of course there is still work to do to better refine the model but certainly a very good start.
If anyone is interested in learning more about Stable Diffusion and how it works you can consult the following Wikipedia link on the topic: https://en.m.wikipedia.org/wiki/Stable_Diffusion