Post

affine
@refinement.systems

I'm trying to replicate the DLSS5 haywire video with open models, no shroom gnomes yet but fun results so far (200 iterations of FLUX.1-schnell and a prompt "Computer, enhance!")

affine
@refinement.systems

Same with SD-Turbo. I'm literally just running torch in a loop with the model, I didn't try replicating normal DLSS operation (I think it's supposed to be `processed_n = model(processed_{n-1}, fresh_n)` or something like that?)

2 reposts24 likes

Abel
@abeliansoup.bsky.social

I’m unhappy with my results in this space thus far (since 21 actually, shocked pikachu) but I’m convinced there’s something here. you might hear from me on this point again one day.. (these are great, not quite what I’m going for though)

Abel
@abeliansoup.bsky.social

you’ll have to be more specific. if you mean these latentgan audioreactive walks then the answer is local only (afaik), but if you mean the conformal cursed Huawei Sun et al warps, also no but I can make a thread if that’d help

affine
@refinement.systems

nah, naively blending the previous previous processed frame with a fresh one is too dumbed down, looks like crap when running it on a video.

affine
@refinement.systems

Could be interesting. Anyway the code is public: bsky.app/profile/did:...

affine@refinement.systems

Ok, I cleaned up the code a bit, but idk if it works after the last minute reorganization into separate scripts: github.com/refinement-s... In any case it currently needs ~33+ GB VRAM to run with all models currently tested, the offload may bring it down to fit in 24, but this was ~10x slower

github.comGitHub - refinement-systems/dltb: Deep Learning Tripping BallsDeep Learning Tripping Balls. Contribute to refinement-systems/dltb development by creating an account on GitHub.