texture-synthesis VS ebsynth

I found the (except when trained exclusively on work you've created during the jam) remark pretty funny, but I suppose someone could train a smaller generative model in the allotted time time (or perhaps use something like texture-synthesis on their own artwork; not sure if that counts as AI).

The submitted article goes above and beyond to guarantee that the code always output the same answer even though it has race conditions. But that's sometimes not possible or, if it's possible, it's too much of a hassle so it's rarely done.

For example, this project https://github.com/EmbarkStudios/texture-synthesis generates textures and if you run the same code with the same input various times, the results will be slightly different. Here https://github.com/EmbarkStudios/texture-synthesis#notes it says: "When using multiple threads for generation, the output image is not guaranteed to be deterministic with the same inputs. To have 100% determinism, you must use a thread count of one"

We are at Embark! https://embark.dev/, https://embark.rs, https://embark.games.

The only AI I can think of would be EbSynth, which would still require some frames to be fixed in Photoshop, but might work.

EbSynth - Transform Video by Painting Over a Single Frame

Download ebsyth from https://ebsynth.com/ , install it. (Make sure your anit-virus did not block it, or else it won't works)

EbSynth (Used to interpolate/animate using painted-over or stylized keyframes from a driving video, à la Joel Haver) https://ebsynth.com/

There is something called ebsynth on GitHub: https://github.com/jamriska/ebsynth

Anything AI is going to be divisive, but I think you already have a pretty good grasp of the issue. Adjacent to this there is stuff like EBSynth https://ebsynth.com/ which rotoscopes video footage. Joel Haver uses it to make all his animations solo and has a video going over the process - https://www.youtube.com/watch?v=tq_KOmXyVDo