xingangpan / draggan Goto Github PK

View Code? Open in Web Editor NEW

35.1K 1.0K 3.4K 34.03 MB

Official Code for DragGAN (SIGGRAPH 2023)

Home Page: https://vcai.mpi-inf.mpg.de/projects/DragGAN/

License: Other

Python 78.80% Cuda 16.56% C++ 4.53% Shell 0.03% Batchfile 0.03% Dockerfile 0.05%

artificial-intelligence generative-adversarial-network generative-models image-manipulation

draggan's People

Contributors

Stargazers

Watchers

Forkers

saxoji andmitsch vcip2015 arvind-india acti0nus melgene-xu gh81997167 cylonspace fraware marciopocebon fukaken5050 sulphuricacidop codesage4 oqtops moku23 alterant ekoziol 5l1v3r1 shirwein weretop carlosrziegler neobine dboudens akshatgarg99 freanchie oriolgallemi yushun1 radoygeorgiev solihe lyhiving andreygermanov godzil21 zhangminxi silvery5d jhurtado2015 stimograph ccpu mustaphau shingii faisalomar sriharshitha842 huseyinzorlu somesh-beep lucasgsantiago tonywhite11 az0xel surfcao cider7 nigglenuts cjh88888 sjyi jubalskaggs haorand rne1223 gopalrk meezyart aidasdir ashishshaiju everilife imemphisxx fnu-avi randomye chinshou light333333 dinodefend corbow6 josedudias xiaojichao colin6618 henry1985 tinghui520 ltyong kulhunter cungle68 cristiancmoises fansun126 commerceless soflyman cj4y shammirbaig liuyangatgdut david-hoa2023 masonbali bkjyyy thuskey gacwr palpitate-xus abdullahasad217 apprikatai maple98 haoweihsueh zhang-tao-whu dingguoli mohudesu osen1978 chkhu vrgz2022 kimx3966 vu1seek ggxkoy

draggan's Issues

AttributeError: module 'legacy' has no attribute 'load_network_pkl'

Running on Windows11 by Git Bash

Traceback (most recent call last):
File "C:\Users\adm\AppData\Local\Programs\Python\Python310\lib\site-packages\viz\renderer.py", line 131, in get_network
data = legacy.load_network_pkl(f)
AttributeError: module 'legacy' has no attribute 'load_network_pkl'

It is suggested to add Baidu Netdisk

Chinese users cannot access Google

666 Release it on June 9

It's my bday! :D

Trying to run on Mac m1

My Mac configs:
os: Mac OS 13.4 (22F66)
cpu: Mac m1
ram: 8GB

after running through
sh scripts/gui.sh

I am getting segment fault:
scripts/gui.sh: line 2: 77912 Segmentation fault: 11 python visualizer_drag.py checkpoints/stylegan2_lions_512_pytorch.pkl

need any more information would be happy to share.

GLFWError

(stylegan3) [root@aigc DragGAN]# ./gui.sh
/root/miniconda3/envs/stylegan3/lib/python3.9/site-packages/glfw/init.py:834: GLFWError: (65544) b'X11: The DISPLAY environment variable is missing'
warnings.warn(message, GLFWError)
/root/miniconda3/envs/stylegan3/lib/python3.9/site-packages/glfw/init.py:834: GLFWError: (65537) b'The GLFW library is not initialized'
warnings.warn(message, GLFWError)
python: /builds/florianrhiem/pyGLFW/glfw-3.3.4/src/input.c:832: glfwSetKeyCallback: Assertion `window != ((void *)0)' failed.
./gui.sh: line 11: 27555 Aborted python visualizer_drag.py checkpoints/stylegan2_lions_512_pytorch.pkl checkpoints/stylegan2-ffhq-512x512.pkl checkpoints/stylegan2-afhqcat-512x512.pkl checkpoints/stylegan2-car-config-f.pkl checkpoints/stylegan2_dogs_1024_pytorch.pkl checkpoints/stylegan2_horses_256_pytorch.pkl checkpoints/stylegan2-cat-config-f.pkl checkpoints/stylegan2_elephants_512_pytorch.pkl checkpoints/stylegan_human_v2_512.pkl checkpoints/stylegan2-lhq-256x256.pkl

Demo page！

Looking forward to publishing relevant operable display webpages, similar to SAM.
Again, it's a great job! 🤩

Hi

What is the License of DragGAN?

DragGAN-main\viz\renderer.py", line 160, in get_network raise NameError('Cannot infer model type from pkl name!') NameError: Cannot infer model type from pkl name!

DragGAN-main\viz\renderer.py", line 160, in get_network
raise NameError('Cannot infer model type from pkl name!')
NameError: Cannot infer model type from pkl name!

The gui seems has problem on loading second plugin

It get stucked while loading upfirdn2d_plugin. No response after 5 minutes

感觉没有宣传得时候那种效果啊是我得姿势不对么头确实转过来了不过换了个脸

How to download and use Drag Gan

I am a newcomer. I learned about Drag Gan through news reports, so I registered and entered this community. I would like to ask everyone how to download and use this software?

nvcc fatal : Unsupported gpu architecture 'compute_86',help!!

4090
x86
ubuntu
cuda:12.0
NVIDIA-SMI 525.105.17

when i run visualizer_drag_gradio.py ,i get this error
(nvcc fatal : Unsupported gpu architecture 'compute_86'
ninja: build stopped: subcommand failed.)
what can i do ,pl

Funny and exciting repo. Received a lot of stars without any code snippets!

Looking forward to the code and model release soon

colab version please！

Error 400/403 happened while running scripts/download_model.sh

drimoon@DESKTOP-1GO1HJO:/mnt/g/DragGAN$ sh scripts/download_model.sh
mkdir: cannot create directory ‘checkpoints\r’: File exists
: not foundnload_model.sh: 3:
--2023-06-26 12:54:13--  https://storage.googleapis.com/self-distilled-stylegan/lions_512_pytorch.pkl%0D
Resolving storage.googleapis.com (storage.googleapis.com)... 172.217.160.112, 142.251.43.16, 142.251.42.240, ...
Connecting to storage.googleapis.com (storage.googleapis.com)|172.217.160.112|:443... connected.
HTTP request sent, awaiting response... 400 Bad Request
2023-06-26 12:54:14 ERROR 400: Bad Request.

mv: cannot stat 'lions_512_pytorch.pkl': No such file or directory
: not foundnload_model.sh: 6:
--2023-06-26 12:54:14--  https://storage.googleapis.com/self-distilled-stylegan/dogs_1024_pytorch.pkl%0D
Resolving storage.googleapis.com (storage.googleapis.com)... 172.217.160.112, 142.251.43.16, 142.251.42.240, ...
Connecting to storage.googleapis.com (storage.googleapis.com)|172.217.160.112|:443... connected.
HTTP request sent, awaiting response... 400 Bad Request
2023-06-26 12:54:15 ERROR 400: Bad Request.

mv: cannot stat 'dogs_1024_pytorch.pkl': No such file or directory
: not foundnload_model.sh: 9:
--2023-06-26 12:54:15--  https://storage.googleapis.com/self-distilled-stylegan/horses_256_pytorch.pkl%0D
Resolving storage.googleapis.com (storage.googleapis.com)... 172.217.160.112, 142.251.43.16, 142.251.42.240, ...
Connecting to storage.googleapis.com (storage.googleapis.com)|172.217.160.112|:443... connected.
HTTP request sent, awaiting response... 400 Bad Request
2023-06-26 12:54:16 ERROR 400: Bad Request.

mv: cannot stat 'horses_256_pytorch.pkl': No such file or directory
: not foundnload_model.sh: 12:
--2023-06-26 12:54:16--  https://storage.googleapis.com/self-distilled-stylegan/elephants_512_pytorch.pkl%0D
Resolving storage.googleapis.com (storage.googleapis.com)... 172.217.160.112, 142.251.43.16, 142.251.42.240, ...
Connecting to storage.googleapis.com (storage.googleapis.com)|172.217.160.112|:443... connected.
HTTP request sent, awaiting response... 400 Bad Request
2023-06-26 12:54:16 ERROR 400: Bad Request.

mv: cannot stat 'elephants_512_pytorch.pkl': No such file or directory
: not foundnload_model.sh: 15:
--2023-06-26 12:54:16--  https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-ffhq-512x512.pkl%0D
Resolving api.ngc.nvidia.com (api.ngc.nvidia.com)... 35.160.252.113, 52.12.123.121
Connecting to api.ngc.nvidia.com (api.ngc.nvidia.com)|35.160.252.113|:443... connected.
HTTP request sent, awaiting response... 400
2023-06-26 12:54:17 ERROR 400: (no description).

--2023-06-26 12:54:17--  https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan2/versions/1/files/stylegan2-afhqcat-512x512.pkl%0D
Resolving api.ngc.nvidia.com (api.ngc.nvidia.com)... 35.160.252.113, 52.12.123.121
Connecting to api.ngc.nvidia.com (api.ngc.nvidia.com)|35.160.252.113|:443... connected.
HTTP request sent, awaiting response... 400
2023-06-26 12:54:18 ERROR 400: (no description).

--2023-06-26 12:54:18--  http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-car-config-f.pkl%0D
Resolving d36zk2xti64re0.cloudfront.net (d36zk2xti64re0.cloudfront.net)... 99.84.224.57, 99.84.224.91, 99.84.224.202, ...
Connecting to d36zk2xti64re0.cloudfront.net (d36zk2xti64re0.cloudfront.net)|99.84.224.57|:80... connected.
HTTP request sent, awaiting response... 403 Forbidden
2023-06-26 12:54:19 ERROR 403: Forbidden.

--2023-06-26 12:54:19--  http://d36zk2xti64re0.cloudfront.net/stylegan2/networks/stylegan2-cat-config-f.pkl%0D
Resolving d36zk2xti64re0.cloudfront.net (d36zk2xti64re0.cloudfront.net)... 99.84.224.57, 99.84.224.91, 99.84.224.202, ...
Connecting to d36zk2xti64re0.cloudfront.net (d36zk2xti64re0.cloudfront.net)|99.84.224.57|:80... connected.
HTTP request sent, awaiting response... 403 Forbidden
2023-06-26 12:54:20 ERROR 403: Forbidden.

RuntimeError: Tried to instantiate dummy base class Event

实在不太清楚是那有问题了，大会帮忙吧，困死了

(base) E:\DragGAN>pip list
Package                 Version
----------------------- ------------
boltons                 23.0.0
brotlipy                0.7.0
certifi                 2023.5.7
cffi                    1.15.1
charset-normalizer      2.0.4
colorama                0.4.6
conda                   23.5.0
conda-content-trust     0.1.3
conda-package-handling  2.1.0
conda_package_streaming 0.8.0
cryptography            39.0.1
filelock                3.12.2
idna                    3.4
Jinja2                  3.1.2
jsonpatch               1.32
jsonpointer             2.1
MarkupSafe              2.1.3
menuinst                1.4.19
mpmath                  1.3.0
networkx                3.1
numpy                   1.25.0
packaging               23.0
Pillow                  9.5.0
pip                     23.1.2
pluggy                  1.0.0
pycosat                 0.6.4
pycparser               2.21
pyOpenSSL               23.0.0
PySocks                 1.7.1
requests                2.29.0
ruamel.yaml             0.17.21
ruamel.yaml.clib        0.2.6
setuptools              65.6.3
six                     1.16.0
sympy                   1.12
toolz                   0.12.0
torch                   2.0.1+cu118
torchaudio              2.0.2+cu118
torchvision             0.15.2+cu118
tqdm                    4.65.0
typing_extensions       4.6.3
urllib3                 1.26.16
wheel                   0.37.1
win-inet-pton           1.1.0
wincertstore            0.2
zstandard               0.19.0

$ sh scripts/gui.sh
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1'
Traceback (most recent call last):
  File "E:\DragGAN\visualizer_drag.py", line 402, in <module>
    main()
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "E:\DragGAN\visualizer_drag.py", line 396, in main
    viz.draw_frame()
  File "E:\DragGAN\visualizer_drag.py", line 168, in draw_frame
    self._async_renderer.set_args(**self.args)
  File "E:\DragGAN\visualizer_drag.py", line 294, in set_args
    self._set_args_sync(**args)
  File "E:\DragGAN\visualizer_drag.py", line 311, in _set_args_sync
    self._renderer_obj = renderer.Renderer()
  File "E:\DragGAN\viz\renderer.py", line 78, in __init__
    self._start_event   = torch.cuda.Event(enable_timing=True)
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\cuda\streams.py", line 164, in __new__
    return super(Event, cls).__new__(
  File "C:\Users\***\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\cuda\_utils.py", line 46, in err_fn
    raise RuntimeError(
RuntimeError: Tried to instantiate dummy base class Event

can i get the codee

how to get the code ? is this opensource ?

How do I use/download it?

Any update for DragGAN code? It's almost July Now!

报错

NameError: name 'inverse_image' is not defined

When trying to import a custom image file, I always receive the error message:

File "PathtoDragGAN\draggan\web.py", line 183, in on_image_change
    result = inverse_image(
NameError: name 'inverse_image' is not defined

牛的

牛的大佬，等着看你们发布

awesome! you are the proud of Chinese

go go go

It's really cool!

Does pre-trained model or code repo is coming soon?

not funtion

not funtion!

Is there any possibility to extend the project as stable diffusion extension

单纯问个, 大佬有打算把它整合进stable diffusion吗？

这对于许多人来说应该会有很大的帮助，尤其是在控制stable diffusion生成奇怪的图之下用于控制然后输出成自己想要的样子

For anyone who want to try DragGAN now, here is an unofficial implementation with Gradio demo

See https://github.com/Zeqiang-Lai/DragGAN

Have fun with it.

demo.mp4

[BUG] OpenGL error ,try pip install PyOpenGL

I try it: export MESA_GL_VERSION_OVERRIDE=3.3. But the following error still occurred, My computer is configured with MAC 2.4 GHz 8-core Intel Core i9

raise self._errorClass(

OpenGL.error.GLError: GLError(
err = 1282,
description = b'invalid operation',
baseOperation = glGetUniformLocation,
cArguments = (1, b'Texture\x00'),
result = -1
)

Goodfellow 发来祝贺orz

uploading pictures online

Please support uploading pictures online for editing

Happy Birthday!

Looking forward to your project.

glfw error

/home/dell/anaconda3/envs/DragGAN/lib/python3.8/site-packages/glfw/init.py:834: GLFWError: (65544) b'X11: Failed to open display '
warnings.warn(message, GLFWError)
/home/dell/anaconda3/envs/DragGAN/lib/python3.8/site-packages/glfw/init.py:834: GLFWError: (65537) b'The GLFW library is not initialized'
warnings.warn(message, GLFWError)
python: /builds/florianrhiem/pyGLFW/glfw-3.3.4/src/input.c:832: glfwSetKeyCallback: Assertion `window != ((void *)0)' failed.
Aborted (core dumped)

[Code Implementation] For anyone who wants to try it rightnow

Feel free to take a look at

https://github.com/endo-yuki-t/UserControllableLT

before the codes are uploaded

(and the amazing Colab from camenduru https://github.com/camenduru/UserControllableLT-colab)

Question: Is this standalone?

Wondering if this is standalone or if i have to use automatic1111. I have a tool I've built from scratch and would love to include this in it. I'll contribute back to the project as well. Amazing work~

Add one of those 'buy my a coffee' links :)

AI再次步入新阶段！

潘老师nb!

期待

看起来它适合做photoshop的插件

AMD GPU

I only have an AMD GPU instead of a Nvidia GPU. Can I still use DragGAN?

GLError

OpenGL.error.GLError: GLError(
err = 1282,
description = b'invalid operation',
baseOperation = glGetUniformLocation,
cArguments = (1, b'Texture\x00'),
result = -1
)

Run on WSL2 windows11

Please close this issue when the code is released.

Folks watching the repo can't actually get updates on a git push. So this placeholder issue is a way for folks to watch for the code drop. Thanks!

Daiiiimmma!

Error: ModuleNotFoundError: No module named 'imgui'

I created a new coda env with Python 3.11 and installed the models, but when I execute the GUI, I encounter this error:

➜ conda create --name dragcan python=3.11

➜ pip install -r requirements.txt                          

➜ sh scripts/gui.sh  
Traceback (most recent call last):
  File "/home/dbugger/projects/ai/DragGAN/visualizer_drag.py", line 15, in <module>
    import imgui
ModuleNotFoundError: No module named 'imgui'

I want to learn the program and contribute to it，can i？

太赞了

期待发布

Windows Instructions

Could you share how to get it working on Windows please?

cool

Look really cool what software do you use

I'd like to contribute to the code, Can I ?

Attribute Error: image

Traceback (most recent call last):
File "C:\Users\alime\Downloads\DragGAN-main1\DragGAN-main\dnnlib\util.py", line 45, in getattr
return self[name]
KeyError: 'image'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\alime\Downloads\DragGAN-main1\DragGAN-main\visualizer_drag.py", line 402, in
main()
File "C:\Users\alime\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1130, in call
return self.main(*args, **kwargs)
File "C:\Users\alime\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1055, in main
rv = self.invoke(ctx)
File "C:\Users\alime\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\alime\AppData\Local\Programs\Python\Python310\lib\site-packages\click\core.py", line 760, in invoke
return __callback(*args, **kwargs)
File "C:\Users\alime\Downloads\DragGAN-main1\DragGAN-main\visualizer_drag.py", line 396, in main
viz.draw_frame()
File "C:\Users\alime\Downloads\DragGAN-main1\DragGAN-main\visualizer_drag.py", line 181, in draw_frame
h, w, _ = self.result.image.shape
File "C:\Users\alime\Downloads\DragGAN-main1\DragGAN-main\dnnlib\util.py", line 47, in getattr
raise AttributeError(name)
AttributeError: image