OnnxStream
OnnxStream copied to clipboard
vitoplantamura
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-...
Hi there, sorry if this is a dumb question but how can i set MAX_SPEED=ON i carnt figure it out many thanks
----------------[start]------------------ positive_prompt: An astronaut riding a horse on Mars negative_prompt: ugly, blurry output_png_path: ./result.png steps: 5 ----------------[prompt]------------------ ----------------[diffusion]--------------- step:0 === ERROR === failed to create multiply operation This is the...
To see how the diffusion is progressing, it would be good to see diffused image stages in - for example - every single steps. The user could use paramter to...
‘’‘It is strongly recommended to run the excellent [ONNX Simplifier](https://github.com/daquexian/onnx-simplifier) on the exported ONNX file before its conversion to a model.txt file. ’‘’ could you upload the onnx model?
Hi, My idea is to implement some sort of logging mechanism. I added my own taste of course, but would be benefitial to implement a light logging. Would you consider...
Can i run with MAX_SPEED=ON with 1gb ram raspberry pi 3b+?
I made it through cmake install, and XNNPACK build without errors, but the OnnxStream build bombs out -- 100%] Built target cpuinfo_internals pi@PI64bit:~/XNNPACK/build $ cd /home/pi pi@PI64bit:~ $ cd OnnxStream...
Dear OnnxStream Developers, I am reaching out to propose an enhancement to integrate OnnxStream as an additional extension with the Automatic1111webui, utilizing RAM rather than VRAM. The rationale behind this...
Hi, Thanks for the repo. I have successfully completed the build on a windows machine using WSL - Ubuntu 2020. Can you please help with what are the next steps...
Hello, I am inquiring about the possibility of utilizing VRAM instead of RAM when OnnxStream. This inquiry stems from the consideration that enabling VRAM usage could potentially allow individuals with...
Metadata
Owner
Metadata
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-...