Post

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

12 Sept

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?)

lynn

@chordbug.bsky.social

12 Sept

so cool, could you try running both on rgb noise?

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.

12/9/26, 10:53 pm0 reposts0 likes

No replies yet.