Art Processing Sharing Blog
This video is an example of a latent diffusion generative ai drift session. The theme is 'the End of Time - a children's story'.
The imagery was generated using a LAION-400M latent diffusion multi-modal generative ai text to image synthesis model. The animation was put together in Studio Artist using Transition Contexts and Paint Action Sequence (PASeq) processing. You see the imagery presented in the order it was created in the live drift session. Drifting is an art process that we originated working with live mutation of procedural MSG (modular synthesized graphics) generative effects in Studio Artist. Here we are extending the live drift concept by working with generative ai image synthesis algorithms. The particular generative synthesis algorithm we are using here is a multi-modal latent diffusion algorithm, but you could just as easily be using a VQGAN or other generative image synthesis techniques.
Drifting is an example of a human artist and a generative ai system working together to create something over time. You can think of drifting as an interactive exploration of the adjustable parameter space of a generative algorithm or art creation system. The idea is to slowly change or adjust the parameter space of the system by some small amount, observe the results, and then continue that cycle. The changes for this particular drift being additional textural input added to or subtracted from the multi-modal text to image generative algorithm, as well as individual adjustments of parameters associated with the image synthesis model. Over time, you are slowly drifting through the generative algorithm's space of creative possibilities.
You need to be a member of Studio Artist to add comments!
Hi, here is a new video, lots of MSG (background layer) and MSG generation path starts along with Time Particles in the paint synth, the "Piggy" figure I made in ZBrush and then animated in Blender, with embedded alpha channel, then took into Studio Artist and made into several different kinds of Movie Brushes. Several layers composited together in Blender. Music made with Bespoke Synth and my Shenai. If anyone has any questions about how it was done I'd be happy to explain more.…
I am not sure if this forum is active anymore... I thought it would be fun to post a very early piece of mine made with, probably, SA3 or 4. I have been a user since 2001.
"Chromosome Rain", 2010
Another experiment painting with Paint Synth vector based presets. Captured rather than output to file.
Either the night sky before the Day of the Triffids - or a closup of Star Treks The…
A capture of a PasEq playback (all I had left after a crash) I didn't save the over sized Paint Synth Presets that I was adjusting and testing... But I did save the PAsEq. This would be what…
Working with Source .png Images Turning the alpha channel on for transparent .png backgrounds When using .png source images with transparent backgrounds, you will need to set Canvas > Selection > Set to > Source Alpha and then Check Mask…
Basics of the Dual Paint Mode, Concepts and How to Create Your Own Dual Paint Presets For More Information on Dual Paint please see this DUAL PAINT POST For More Information DUAL PAINT POST
The post…
How to Erase the Canvas To erase the canvas choose the Eraser Icon at the top of the Interface or choose Canvas > Erase to See this Post for more detailed information on the canvas eraser options.
The post…
Everything You Need to Know about Studio Artist Presets and Preset Management
The post Preset Management Video appeared first on Studio Artist…
Resizing the Canvas Please see this tip on Resizing the Canvas And how to Resize the Canvas for High-Resolution Print
The post Resizing the Canvas appeared first on…
Comments
Can't wait to see where SA 6 lands us :)
It's funny, because this video piece isn't all that old, but what the latent diffusion image synthesis algorithm is doing in it is totally out of date. Compared to the new latent diffusion image synthesis prototypes we're working with nowdays.
I'm working out some new workflows incorporating these new AI tools and SA. I love the results. Next step is to workout some blending options for video creation.. so this latent diffusion seems like a good option, as well as optical flow (provides some nice effects)
I'd love to hear more about your current experiments. What ai approaches are you using, and how are you incorporating SA into the workflow?