diff --git a/README.md b/README.md index 0778eaa..845e217 100644 --- a/README.md +++ b/README.md @@ -21,6 +21,8 @@ This repository integrates all the tricks I know to speed up Flux inference: ### For Flux +Flux Generation Results + You can use `XXCache`, `SageAttention`, and `torch.compile` with the following examples: FBCache diff --git a/assets/flux_generation_results.png b/assets/flux_generation_results.png new file mode 100644 index 0000000..1454185 Binary files /dev/null and b/assets/flux_generation_results.png differ