-
Notifications
You must be signed in to change notification settings - Fork 221
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Image generation doesnt work. #27
Comments
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. |
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. |
It seems a bit unusual. You can try turning off AVX and see how it goes.
or
|
(Cuda) PS D:\stable-diffusion.cpp> ./build/bin/Release/sd.exe -m "D:\stable-diffusion.cpp\models\v1-5-pruned-emaonly-ggml-model-f32.bin" -p "neko, catgirl, cute" -o "D:\stable-diffusion.cpp\outputs\output.png" -v -t 12
Option:
n_threads: 12
mode: txt2img
model_path: D:\stable-diffusion.cpp\models\v1-5-pruned-emaonly-ggml-model-f32.bin
output_path: D:\stable-diffusion.cpp\outputs\output.png
init_img:
prompt: neko, catgirl, cute
negative_prompt:
cfg_scale: 7.00
width: 512
height: 512
sample_method: eular a
sample_steps: 20
strength: 0.75
seed: 42
System Info:
BLAS = 0
SSE3 = 1
AVX = 1
AVX2 = 1
AVX512 = 0
AVX512_VBMI = 0
AVX512_VNNI = 0
FMA = 1
NEON = 0
ARM_FMA = 0
F16C = 1
FP16_VA = 0
WASM_SIMD = 0
VSX = 0
[INFO] stable-diffusion.cpp:2687 - loading model from 'D:\stable-diffusion.cpp\models\v1-5-pruned-emaonly-ggml-model-f32.bin'
[DEBUG] stable-diffusion.cpp:2695 - verifying magic
[DEBUG] stable-diffusion.cpp:2706 - loading hparams
[INFO] stable-diffusion.cpp:2712 - ftype: f32
[DEBUG] stable-diffusion.cpp:2718 - loading vocab
[DEBUG] stable-diffusion.cpp:2746 - ggml tensor size = 272 bytes
[DEBUG] stable-diffusion.cpp:2751 - clip params ctx size = 470.72 MB
[DEBUG] stable-diffusion.cpp:2770 - unet params ctx size = 2156.43 MB
[DEBUG] stable-diffusion.cpp:2791 - vae params ctx size = 95.51 MB
[DEBUG] stable-diffusion.cpp:2812 - preparing memory for the weights
[DEBUG] stable-diffusion.cpp:2828 - loading weights
[DEBUG] stable-diffusion.cpp:2932 - model size = 2719.24MB
[INFO] stable-diffusion.cpp:2941 - total params size = 2719.53MB (clip 469.50MB, unet 2155.53MB, vae 94.51MB)
[INFO] stable-diffusion.cpp:2943 - loading model from 'D:\stable-diffusion.cpp\models\v1-5-pruned-emaonly-ggml-model-f32.bin' completed, taking 43.51s
(Cuda) PS D:\stable-diffusion.cpp>
It stops and there is no output.
The text was updated successfully, but these errors were encountered: