diff --git a/README.md b/README.md
index f54f3c3..b29f852 100644
--- a/README.md
+++ b/README.md
@@ -12,6 +12,8 @@ GPT2-XL 1.3B on A40 (tf32) = 0.032 sec/token (for ctxlen 1000), tested using HF,
 
 Training speed: RWKV-4 1.5B BF16 ctxlen1024 = 106K tokens/s on 8xA100 40G.
 
+I am doing image experiments too (For example: https://huggingface.co/BlinkDL/clip-guided-binary-autoencoder) and RWKV will be able to do txt2img diffusion :) My idea: 256x256 rgb image -> 32x32x13bit latents -> apply RWKV to compute transition probability for each of the 32x32 grid -> pretend the grids are independent and "diffuse" using these probabilities.
+
 ## Join our Discord: https://discord.gg/bDSBUMeFpc :)
 
 You are welcome to join the RWKV discord https://discord.gg/bDSBUMeFpc to build upon it. We have plenty of potential compute (A100 40Gs) now (thanks to Stability and EleutherAI), so if you have interesting ideas I can run them.