Comments (3)
I'm using the same model on Windows 10, but I'm not able to reproduce this issue. It seems like the problem is occurring right after loading the weights and then exiting. Would you mind sharing the Windows version you're using, your CPU model, your computer's memory size, and your Visual Studio version? If possible, you can also try downloading the executable from https://github.com/leejet/stable-diffusion.cpp/releases to see if it helps, and you can try it with or without the avx.
from stable-diffusion.cpp.
I did build and run it with wsl, but building and running on my xeon does the same as above.
It seems a bit unusual. You can try turning off AVX and see how it goes.
cmake .. -DGGML_AVX2=OFF
cmake --build . --config Release
or
cmake .. -DGGML_AVX2=OFF -DGGML_AVX=OFF
cmake --build . --config Release
from stable-diffusion.cpp.
I have the same issue when I build it, win 10: 19045, xeon w5-2455x, 128gb ddr5 and vs 2022
I did build and run it with wsl, but building and running on my xeon does the same as above.
from stable-diffusion.cpp.
Related Issues (20)
- [Feature Request] Embeddings like EasyNegative HOT 2
- Error with quantization and lora HOT 2
- Build fails on mingw
- Presets or enhancing output
- Generate another image without loading the model again HOT 3
- Is there anyone who can't generate images correctly? HOT 11
- Roop/Face Swap?
- UNet is not run with GPU HOT 6
- Metal build with SDXL-Turbo generates a black output image HOT 4
- Exception when delete StableDiffusion pointer HOT 2
- FreeU support HOT 8
- Flash attention abort trap HOT 9
- C-API export seems to not work correctly HOT 4
- std::set undefined HOT 1
- Can not release memory HOT 7
- Stable Diffusion with LCM on Mac OS(Metal) produces black image HOT 1
- Metal backend doesn't gain a speed bonus from running with half precision HOT 1
- Problems with function "ggml_quantize_chunk" on M1 in ggml.c HOT 1
- Enhance:free_params_immediately can be infer again HOT 4
- Support for splitting buffers M1/M2/M3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stable-diffusion.cpp.