update new models

.gitattributes

@@ -1,3 +1,4 @@
 *.png filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,6 +16,12 @@ widget:
 
 # BPModel
 
+## Update
+
+2023-01-02: I wasted more GPU hours to train it a little bit more (overfitting). Check out [bp_mk3.safetensors](bp_mk3.safetensors) and [bp_mk5.safetensors](bp_mk5.safetensors). Prepare yourself own VAE! Update your WebUI if you can't load [safetensors](https://github.com/huggingface/safetensors).
+
+## Introduction
+
 BPModel is an experimental Stable Diffusion model based on [ACertainty](https://huggingface.co/JosephusCheung/ACertainty) from [Joseph Cheung](https://huggingface.co/JosephusCheung). 
 
 Why is the Model even existing? There are loads of Stable Diffusion model out there, especially anime style models.
@@ -145,7 +151,7 @@ LaTeNt SpAcE!
 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
 EMA weight is not included and it's fp16.
 
-If you want to continue training, use [`bp_1024_e10_ema.ckpt`](bp_1024_e10_ema.ckpt) which is the ema weight 
+If you want to continue training, use [`bp_1024_e10_ema.ckpt`](bp_1024_e10_ema.ckpt) which is the ema unet weight 
 and with fp32 precision.
 
 For better performance, it is strongly recommended to use Clip skip (CLIP stop at last layers) 2.

bp_mk3.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97848d7d80b242a1483d0307509b422fee12a0e7096ff202397a6e395a71aea9
+size 1719136903

bp_mk5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87dabceffd299a8f3f72f031829338e34ad3c1e2541815af08fa694d65fb4c0
+size 1719136903