zhl1bug commited on
Commit
1126b94
1 Parent(s): b8abb43

submit best ckpt

Browse files
.gitattributes CHANGED
@@ -32,3 +32,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ paddle_lora_weights.pdparams filter=lfs diff=lfs merge=lfs -text
36
+ validation_images/200.png filter=lfs diff=lfs merge=lfs -text
37
+ validation_images/300.png filter=lfs diff=lfs merge=lfs -text
38
+ validation_images/400.png filter=lfs diff=lfs merge=lfs -text
39
+ validation_images/500.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,21 @@
 
1
  ---
2
- license: gpl-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
1
+
2
  ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
5
+ instance_prompt: a photo of sks cat in a bucket
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-ppdiffusers
9
+ - text-to-image
10
+ - ppdiffusers
11
+ - lora
12
+ inference: false
13
  ---
14
+
15
+ # LoRA DreamBooth - zhl1bug/lora_sks_cats
16
+ 本仓库的 LoRA 权重是基于 stabilityai/stable-diffusion-2-1 训练而来的,我们采用[DreamBooth](https://dreambooth.github.io/)的技术并使用 a photo of sks cat in a bucket 文本进行了训练。 下面是在训练过程中生成的一些图片。
17
+ ![img_0](validation_images/500.png)
18
+ ![img_0](validation_images/400.png)
19
+ ![img_0](validation_images/300.png)
20
+ ![img_0](validation_images/200.png)
21
+
paddle_lora_weights.pdparams ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0a621d22cba04a2f4ee612ee590f5abc9eb76c3315b5b87e2d189d24f87f77
3
+ size 3357150
untitled.gradio.py ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #该应用创建工具共包含三个区域,顶部工具栏,左侧代码区,右侧交互效果区,其中右侧交互效果是通过左侧代码生成的,存在对照关系。
2
+ #顶部工具栏:运行、保存、新开浏览器打开、实时预览开关,针对运行和在浏览器打开选项进行重要说明:
3
+ #[运行]:交互效果并非实时更新,代码变更后,需点击运行按钮获得最新交互效果。
4
+ #[在浏览器打开]:新建页面查看交互效果。
5
+ #以下为应用创建工具的示例代码
6
+
7
+ import gradio as gr
8
+
9
+ def quickstart(name):
10
+ return "欢迎使用BML CodeLab应用创建工具Gradio, " + name + "!!!"
11
+ demo = gr.Interface(fn=quickstart, inputs="text", outputs="text")
12
+
13
+ demo.launch()
upload.py ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from utils import upload_lora_folder
2
+ upload_dir = "cats" # 我们需要上传的文件夹目录
3
+ repo_name = "CatsSnowforest" # 我们需要上传的repo名称
4
+ pretrained_model_name_or_path = "runwayml/stable-diffusion-v1-5" # 训练该模型所使用的基础模型
5
+ prompt = "a cat looking at the Snow forest" # 搭配该权重需要使用的Prompt文本
6
+
7
+ upload_lora_folder(
8
+ upload_dir=upload_dir,
9
+ repo_name=repo_name,
10
+ pretrained_model_name_or_path=pretrained_model_name_or_path,
11
+ prompt=prompt,
12
+ )
validation_images/.ipynb_checkpoints/100-checkpoint.png ADDED
validation_images/.ipynb_checkpoints/200-checkpoint.png ADDED
validation_images/.ipynb_checkpoints/300-checkpoint.png ADDED
validation_images/.ipynb_checkpoints/400-checkpoint.png ADDED
validation_images/.ipynb_checkpoints/500-checkpoint.png ADDED
validation_images/200.png ADDED

Git LFS Details

  • SHA256: 599b788f127501ae156772888a5c77e339d894a7f379173cf2ef64454f87d370
  • Pointer size: 132 Bytes
  • Size of remote file: 1.67 MB
validation_images/300.png ADDED

Git LFS Details

  • SHA256: b843c14f6c9accc1b47bfdfafdee4828f4e36cbab585271812d59b3d72737614
  • Pointer size: 132 Bytes
  • Size of remote file: 1.56 MB
validation_images/400.png ADDED

Git LFS Details

  • SHA256: 988c31a4ce552892f62af1cc3842ceb348ef5e1203d8e41d901166ac222b9b34
  • Pointer size: 132 Bytes
  • Size of remote file: 1.33 MB
validation_images/500.png ADDED

Git LFS Details

  • SHA256: b25f6772e891537f39f3d8d4ad6d126fb4f6d8c7e56391b76483e0b531dfbeb9
  • Pointer size: 132 Bytes
  • Size of remote file: 1.51 MB