We're back baby! (Update and Roadmap) (Patreon)

Thanks for hanging out while I had a bit of a decompression week, I'll be back at some set creation today and will be aiming to ramp up production through March now that I've got two editors to take on the outputs. Your voting and request submissions have been helpful in giving me a roadmap for the month, and I have a few more Duo sets on deck I want to get in the mix. 

While awaiting for Stable Diffusion 3 to be publicly available and compatible with this genre of art, I'm going to be diving into some Stable Diffusion XL research (basically Stable Diffusion 2) and will see how this intermediary workflow quality compares to the output and flexibility of my current refined process.

I also am seeing some improvement in the AnimateDiff video creation which can essentially allow me to turn any of the output images into short videos depicting what is occurring in the static image, so I want to see what I can do with that. You may have also come across Alibaba's announcement and samples of it's EMO AI which can apply any audio into a high fidelity lipsync process. I'm thinking once there's open source access to both of these two branches, they can be combined into some pretty impressive action shot videos that retain the immersion and artistic flair of our brand - I have been delaying video development until I can be confident I can output something more impressive than a simple face swap onto a seemingly unrelated video background/theme etc. 

Lastly, if your long term support and community growth continues on the trend I have been forecasting, by early 2025 I may be able to transition to full time commitment to this project and go on a hiatus from my current career. This will further accelerate output quality and quantity, and I would have all of you to personally attribute this improvement to :) Onwards and upwards friends!