azula.guidance.cfg

Classifier-free guidance (CFG) internals.

References

Classifier-Free Diffusion Guidance (Ho et al., 2022)
https://arxiv.org/abs/2207.12598

Classes

CFGDenoiser

Creates a CFG denoiser module.

Descriptions

class azula.guidance.cfg.CFGDenoiser(denoiser)

Creates a CFG denoiser module.

Parameters:

denoiser (GaussianDenoiser) – A Gaussian denoiser.

forward(x_t, t, positive, negative={}, guidance=1.0, **kwargs)
Parameters:

  • x_t (Tensor) – A noisy tensor \(x_t\), with shape \((B, *)\).

  • t (Tensor) – The time \(t\), with shape \(()\) or \((B)\).

  • positive (Dict[str, Any]) – The positive label \(c_+\) as a dictionary of keyword arguments.

  • negative (Dict[str, Any]) – The negative label \(c_-\) as a dictionary of keyword arguments.

  • guidance (float | Tensor) – The classifier-free guidance strength \(\omega \in \mathbb{R}_+\).

  • kwargs – Optional keyword arguments.

Returns:

The Gaussian \(\mathcal{N}(X \mid \mu_\phi(x_t \mid c), \Sigma_\phi(x_t \mid c))\).

Return type:

Gaussian