Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
stablediffusion_v2.1_pytorch
Commits
4a01a1fb
Commit
4a01a1fb
authored
May 17, 2024
by
lijian6
Browse files
Add model.properties
parent
049f76e2
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
22 additions
and
11 deletions
+22
-11
README.md
README.md
+12
-11
model.properties
model.properties
+10
-0
No files found.
README.md
View file @
4a01a1fb
...
...
@@ -26,32 +26,33 @@ cd docker
docker build --no-cache -t stablediffussion:test .
docker run --rm --shm-size 10g --network=host --name=stablediffussion_v2-1 --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -it stablediffussion:test bash
```
### 下载Stable Diffusion v2.1模型
## 数据集
无
## 推理
### 1、下载Stable Diffusion v2.1模型
```
cd /stablediffusion-main
## 下载 SD v2.1 model
git lfs install
git clone https://huggingface.co/stabilityai/stable-diffusion-2-1-base
```
## 数据集
无
## 推理
###
1
、运行
txt2img.py示例
:
运行:
###
2
、运行:
运行
txt2img.py示例
:
```
cd /stablediffusion-main
python scripts/txt2img.py --device cuda --prompt "a photograph of an astronaut riding a horse" --ckpt ./stable-diffusion-2-1-base/v2-1_512-ema-pruned.ckpt --config configs/stable-diffusion/v2-inference.yaml --n_iter 1 --n_samples 1
```
### 2、使用
diffusers
库测试
:
运行
diffusers
示例
:
```
python test_diffusers.py
```
## result

## 精度
##
#
精度
无
## 应用场景
...
...
@@ -59,10 +60,10 @@ python test_diffusers.py
`以文生图`
### 热点应用行业
`绘画,动漫`
`绘画,动漫
,媒体
`
## 源码仓库及问题反馈
http://developer.hpccube.com/codes/modelzoo/stablediffusion_v2.1_pytorch.git
## 参考
## 参考
资料
https://github.com/Stability-AI/stablediffusion
model.properties
0 → 100644
View file @
4a01a1fb
# 模型编码
modelCode
=
630
# 模型名称
modelName
=
stablediffusion_v2.1_pytorch
# 模型描述
modelDescription
=
基于pytorch框架的stablediffusion version2文图生成推理示例
# 应用场景(多个标签以英文逗号分割)
appScenario
=
推理,以文生图,绘画,动漫,媒体
# 框架类型(多个标签以英文逗号分割)
frameType
=
pytorch
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment