Independent publisher
Rohan Nagabhirava
RohanNaga
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: cc-by-4.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Datasets
Derived from the public raw dataset RohanNaga/doom-dense-arnold: every tic of each episode encoded once through a frozen Stable Diffusion autoencoder, stored as one.npy per episode plus a.npz sidecar with the per-tic metadata. Released so that a training run can start without re-encoding, and so that latents are reproducible bit for bit: latent bytes depend on the autoencoder, its scaling, the precision and the encode batch size, all recorded in encodemeta.json inside each folder. Frames are 320x240 padded to 320x256 with mid-gray before encoding; decoders crop the padding ([:,:,:240] in pixels, the last row block in latents). Encoding is bf16 autocast at the batch size named in…