DiT-XL/4 — the XL backbone at patch 4.
Model Size
Parameters
pretrainedbool= FalseNo DiT checkpoint was published for this configuration;
True
raises rather than returning a randomly initialised model.**overridesobject= {}Optional
DiTConfig field overrides.Returns
DiTModelThe denoising network.
Notes
Reference: Peebles and Xie, "Scalable Diffusion Models with Transformers", ICCV, 2023 (arXiv:2212.09748), Table 1 — 28 layers, hidden 1152, 16 heads.
Examples
>>> from lucid.models import dit_xlarge_4
>>> config = dit_xlarge_4().config
>>> config.depth, config.hidden_size, config.patch_size
(28, 1152, 4)