diff --git a/LDM_TRAINER.md b/LDM_TRAINER.md
index 89bb864..77694ed 100644
--- a/LDM_TRAINER.md
+++ b/LDM_TRAINER.md
@@ -167,6 +167,9 @@ The performance is greatly improved by applying classifier-free diffusion guidan
 
 
 ### FID
+https://lightning.ai/docs/torchmetrics/stable/image/frechet_inception_distance.html
+https://en.wikipedia.org/wiki/Fr%C3%A9chet_inception_distance
+
 ### Inception Score
 
 ## LDM Training Configuration
@@ -245,4 +248,4 @@ SD V1.4 [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-di
 
 
 ## Observations from initial training runs
-- a larger batch size stabilizes the gradients. Training on small batch size results in very noisy generated images.
\ No newline at end of file
+- a larger batch size stabilizes the gradients. Training on small batch size results in very noisy generated images.