Generative module (AtomisticGenerator, hooks, pipelines)#
The generative API drives inference for generative models of any family —
diffusion / flow matching, GANs, VAEs, normalizing flows — through the
AtomisticGenerator driver: an optional condition step
followed by generation, with lifecycle hooks, streaming, and sequential
composition. For orientation and recipes, see the
generative models user guide.
Core classes#
Generative inference driver: optionally condition the inputs, generate, optionally materialize to a |
|
Callable that encapsulates a family-specific generation strategy. |
|
Translate a call's raw request into the generating function's working input. |
|
Stages of the |
|
Context object passed to generation hooks. |
|
Sequential composition of generation and batch-processing stages. |
Model-side API#
Pydantic config schema for a generative (non-energy) model. |
|
Mixin class for models designed for generative workflows. |
Demo models#
Minimal GAN-side demo: a latent draw decoded to a point cloud. |
|
Minimal diffusion-side demo: an x0-predictor over point clouds. |