GithubHelp home page GithubHelp logo

Comments (5)

nerdyrodent avatar nerdyrodent commented on July 22, 2024

I would have thought so as Facebook fixed the issue with MS Windows failing just recently :)

from diffusers.

Echolink50 avatar Echolink50 commented on July 22, 2024

Thomas-MMJ posted this on the xformers GitHub

"Can confirm it works and gives speed up. Using https://github.com/ShivamShrirao/diffusers/ - which uses xformers in the attention path for diffusers, I get about a 40% speedup on windows.

Currently trying to get it working on the AUTOMATIC1111 fork and it is not working yet. See discussion here,

AUTOMATIC1111/stable-diffusion-webui#1003"

So I guess someone has already used it. Hopefully that means the same <10gb vram usage.

from diffusers.

78Alpha avatar 78Alpha commented on July 22, 2024

Xformers had been up and running on automatic since a few days ago, should be ready for here.

from diffusers.

KhoaVo avatar KhoaVo commented on July 22, 2024

I tried to install the xformers windows build (provided by automatic) here
https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl

However when I run train_dreambooth.py i get

Could not find module 'C:\Users\user1\.conda\envs\diffusersDreamboth\Lib\site-packages\xformers\_C.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
WARNING:root:WARNING: Could not find module 'C:\Users\user1\.conda\envs\diffusersDreamboth\Lib\site-packages\xformers\_C.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
Need to compile C++ extensions to get sparse attention suport. Please run python setup.py build develop

You can also get this error by doing
import xformers
in the python terminal

I noticed that the automatic repo imports it like this instead
import xformers.ops and it works fine there

Any idea what's going on?

from diffusers.

Echolink50 avatar Echolink50 commented on July 22, 2024

I tried to install the xformers windows build (provided by automatic) here https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl

However when I run train_dreambooth.py i get

Could not find module 'C:\Users\user1\.conda\envs\diffusersDreamboth\Lib\site-packages\xformers\_C.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
WARNING:root:WARNING: Could not find module 'C:\Users\user1\.conda\envs\diffusersDreamboth\Lib\site-packages\xformers\_C.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
Need to compile C++ extensions to get sparse attention suport. Please run python setup.py build develop

You can also get this error by doing import xformers in the python terminal

I noticed that the automatic repo imports it like this instead import xformers.ops and it works fine there

Any idea what's going on?

Not sure but You might need Visual Studio with c++ extension.

from diffusers.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.