From f514f06b1eabec3755ccaa015e26ec0195c0207b Mon Sep 17 00:00:00 2001
From: yuanzhiqiang <yuanzhiqiang@kuaishou.com>
Date: Sat, 6 May 2023 17:36:18 +0800
Subject: [PATCH] updated

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index a16dda3..9def802 100644
--- a/README.md
+++ b/README.md
@@ -17,7 +17,7 @@ Follow and thanks [original training repo](https://github.com/justinpinkney/stab
 
 We used RS image-text dataset [RSITMD](https://github.com/xiaoyuan1996/AMFMN) as training data and fine-tuned stable diffusion for 10 epochs with 1 x A100 GPU.
 When the batchsize is 4, the GPU memory consumption is about 40+ Gb during training, and about 20+ Gb during sampling.
-The pretrain weights is realesed at [last-pruned.ckpt](https://github.com/xiaoyuan1996/AMFMN).
+The pretrain weights is realesed at [last-pruned.ckpt](https://drive.google.com/drive/folders/10vK3eNpIw7H3lxxZbB7NF2IZktGt95As?usp=sharing).
 
 ## Using