Has Anyone Trained This Model Yet?

lucidrains / gigagan-pytorch

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

MIT License

1.82k stars 105 forks source link

Has Anyone Trained This Model Yet? #48

Open PaulFidika opened 1 year ago

PaulFidika commented 1 year ago

Has anyone trained a sample model of this? I realize full-scale training on LAION will take quite a bit of resources (SD v2 trained for 200k GPU hours), but I'm wondering (1) are there any publicly-available sample trained models yet, and (2) any estimate on the resources required for a full-scale training? I'm guessing GigaGan will require less training than Stable Diffusion did.

rosmur commented 5 months ago

Yeah a trained model would be great so that this tech can actually be used.

PaulFidika commented 5 months ago

I totally forgot about this model; has anyone ended up training a version of this? Looks like this codebase hasn't been updated in 5 months.