dit_xlarge_2_gen(pretrained: bool | str = False, weights: DiTXLarge2Weights | None = None, overrides: object = {})dit_xlarge_2 posed as a diffusion sampler.
Model Size
Parameters
pretrainedbool or str= FalseLoad a released checkpoint.
True takes IMAGENET1K_256;
"IMAGENET1K_512" selects the 512-pixel model and moves
sample_size to the 64-side latent it was trained on. These
are the only two DiT checkpoints ever published, and they are
CC-BY-NC-4.0.An explicit tag, taking precedence over
pretrained.**overridesobject= {}Optional
DiTConfig field overrides.Returns
DiTForImageGenerationExposes the denoising objective and generate.
Notes
Reference: Peebles and Xie, arXiv:2212.09748, 2023.
Examples
>>> from lucid.models import dit_xlarge_2_gen
>>> model = dit_xlarge_2_gen()