submit best ckpt

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+paddle_lora_weights.pdparams filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,21 @@
+
+---
+license: creativeml-openrail-m
+base_model: Linaqruf/anything-v3.0
+instance_prompt: hoshino_ai, star_pupils, 1girl
+tags:
+- stable-diffusion
+- stable-diffusion-ppdiffusers
+- text-to-image
+- ppdiffusers
+- lora
+inference: false
+---
+    
+# LoRA DreamBooth - f3rry/hoshino_ai
+本仓库的 LoRA 权重是基于 Linaqruf/anything-v3.0 训练而来的，我们采用[DreamBooth](https://dreambooth.github.io/)的技术并使用 hoshino_ai, star_pupils, 1girl 文本进行了训练。 下面是在训练过程中生成的一些图片。
+ ![img_0](validation_images/2000.png)
+![img_0](validation_images/1800.png)
+![img_0](validation_images/1600.png)
+![img_0](validation_images/1400.png)
+

paddle_lora_weights.pdparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:726c92e17e770110d141ee158864f41082682c09ddc3d9ba51f9fdf3b7d66013
+size 25548778