Crosstyan commited on
Commit
7395ca4
1 Parent(s): fd1f65b
Files changed (2) hide show
  1. README.md +3 -0
  2. bp_1024_e10_ema.ckpt +3 -0
README.md CHANGED
@@ -145,6 +145,9 @@ LaTeNt SpAcE!
145
  Use [`bp_1024_with_vae_te.ckpt`](bp_1024_with_vae_te.ckpt) if you don't have VAE and text encoder with you, still
146
  EMA weight is not included and it's fp16.
147
 
 
 
 
148
  For better performance, it is strongly recommended to use Clip skip (CLIP stop at last layers) 2.
149
 
150
  ## About the Model Name
 
145
  Use [`bp_1024_with_vae_te.ckpt`](bp_1024_with_vae_te.ckpt) if you don't have VAE and text encoder with you, still
146
  EMA weight is not included and it's fp16.
147
 
148
+ If you want to continue training, use [`bp_1024_e10_ema.ckpt`](bp_1024_e10_ema.ckpt) which is the ema weight
149
+ and with fp32 precision.
150
+
151
  For better performance, it is strongly recommended to use Clip skip (CLIP stop at last layers) 2.
152
 
153
  ## About the Model Name
bp_1024_e10_ema.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62854e4c4817c2b515e1b1a13b1ec8498ba71fdbd492496f021a4d257698d0b
3
+ size 3438324709