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
IDM-VTON_pytorch
Commits
9cf34b9d
Commit
9cf34b9d
authored
Jun 27, 2024
by
mashun1
Browse files
Update README.md
parent
6ec994f9
Pipeline
#1266
canceled with stages
Changes
1
Pipelines
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
9 additions
and
5 deletions
+9
-5
README.md
README.md
+9
-5
No files found.
README.md
View file @
9cf34b9d
...
...
@@ -115,9 +115,9 @@ DressCode
### 模型下载
https://hf-mirror.com/yisol/IDM-VTON
[
hugging-face
](
https://hf-mirror.com/yisol/IDM-VTON
)
|
[
SCNet
](
http://113.200.138.88:18080/aimodels/IDM-VTON
)
https://hf-mirror.com/yisol/IDM-VTON-DC
[
hugging-face
](
https://hf-mirror.com/yisol/IDM-VTON-DC
)
|
[
SCNet
](
)
ckpt/
├── densepose
...
...
@@ -175,7 +175,7 @@ https://hf-mirror.com/yisol/IDM-VTON-DC
--pretrained_model_name_or_path <path/to/pretrained_models> \
--output_dir "result" \
--unpaired \
--data_dir
"DATA_DIR"
\
--data_dir
<path/to/datasets/viton-hd>
\
--seed 42 \
--test_batch_size 1 \
--guidance_scale 2.0
...
...
@@ -188,16 +188,20 @@ https://hf-mirror.com/yisol/IDM-VTON-DC
--unet_path <path/to/pretrained_models/dc> \
--output_dir "result" \
--unpaired \
--data_dir
"DATA_DIR"
\
--data_dir
<path/to/datasets/dress-code>
\
--seed 42
--test_batch_size 1
--guidance_scale 2.0
--category "upper_body"
注意:以上默认使用多卡推理,可使用
`export HIP_VISIBLE_DEVICES=<设备号>`
进行限制。
### webui
python gradio_demo/app.py
注意:需要修改
`gradio_demo/app.py`
中
`base_path='path/to/pretrained_models'`
。
## result
|model|image|cloth|prompt|result|
...
...
@@ -214,7 +218,7 @@ https://hf-mirror.com/yisol/IDM-VTON-DC
### 算法类别
`
虚拟换装
`
`
AIGC
`
### 热点应用行业
...
...
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