@johnowhitaker in the [Stable Diffusion Deep Dive.ipynb](https://github.com/fastai/diffusion-nbs/blob/master/Stable%20Diffusion%20Deep%20Dive.ipynb) notebook, section **The UNET and CFG**. You get `latents_x0` because the scheduler exposes `pred_original_sample` ```python latents_x0 = scheduler.step(noise_pred, t, latents).pred_original_sample # Using the scheduler (Diffusers 0.4 and above) ``` How to get this `pred_original_sample` when using `PNDMScheduler`? As this scheduler does not expose this value.