From 1a244e4ddc5c2d76b614af7f7a81b099cedc335d Mon Sep 17 00:00:00 2001 From: Wagner Bruna Date: Fri, 20 Mar 2026 22:58:17 -0300 Subject: [PATCH] docs: update Spectrum info about DiT models --- docs/caching.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/caching.md b/docs/caching.md index cb103aee2..b02a541b7 100644 --- a/docs/caching.md +++ b/docs/caching.md @@ -11,7 +11,7 @@ Caching methods accelerate diffusion inference by reusing intermediate computati | `dbcache` | DiT models | Block-level L1 residual threshold | | `taylorseer` | DiT models | Taylor series approximation | | `cache-dit` | DiT models | Combined DBCache + TaylorSeer | -| `spectrum` | UNET models | Chebyshev + Taylor output forecasting | +| `spectrum` | UNET and DiT models | Chebyshev + Taylor output forecasting | ### UCache (UNET Models) @@ -111,9 +111,9 @@ Mask values: `1` = compute, `0` = can cache. --scm-policy dynamic ``` -### Spectrum (UNET Models) +### Spectrum (UNET and DiT Models) -Spectrum uses Chebyshev polynomial fitting blended with Taylor extrapolation to predict denoised outputs, skipping entire UNet forward passes. Based on the paper [Spectrum: Adaptive Spectral Feature Forecasting for Efficient Diffusion Sampling](https://github.com/tingyu215/Spectrum). +Spectrum uses Chebyshev polynomial fitting blended with Taylor extrapolation to predict denoised outputs, skipping entire forward passes. Based on the paper [Spectrum: Adaptive Spectral Feature Forecasting for Efficient Diffusion Sampling](https://github.com/tingyu215/Spectrum). ```bash sd-cli -m model.safetensors -p "a cat" --cache-mode spectrum