vitoplantamura / OnnxStream

Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK.
https://yolo.vitoplantamura.com/
Other
1.86k stars 84 forks source link

=== ERROR === read_file: unable to open file errors... #31

Closed nich2408 closed 1 year ago

nich2408 commented 1 year ago

Just built the project on my raspberry pi 3b+, but everytime I launch it I get "unable to open file" error.

First I tried: ./sd --models-path /home/pi/ai-projects/stable_diffusion_models_onnxstream/ --rpi where /home/pi/ai-projects/stable_diffusion_models_onnxstream/ is a directory created by myself in which I put the .rar downloaded from github Releases page (win-x64-with-weights) but it gave me: === ERROR === unable to open file: ./tokenizer/vocab.txt like #20

So i created tokenizer directory and copied the vocab.txt from the models directory but then it gave me: === ERROR === read_file: unable to open file (./text_encoder_fp32/model.txt).

Am I doing something wrong? Does the models directory have some strict requirements?

Thanks

vitoplantamura commented 1 year ago

hi,

you should simply unzip the rar file :-)

Vito

nich2408 commented 1 year ago

Hi, I already unzipped it but nothing, I used unrar package (Ubuntu). Sorry If I didnt make it clear In the unzipped there isn't tokenizer directory Maybe I'm using unrar command the wrong way, I'll try again later

jaydenchan1027 commented 1 year ago

hi, you should simply unzip the rar file :-) Vito

Where is the rar file

vitoplantamura commented 1 year ago

here: https://github.com/vitoplantamura/OnnxStream/releases/download/v0.1/StableDiffusion-OnnxStream-Windows-x64-with-weights.rar

Vito

nich2408 commented 1 year ago

Ok solved, to unrar it on Ubuntu i had to use unrar - x - r which keeps the folder structure. Thanks for the help Vito, this project is great and the guide is clear