104 karma · joined April 22, 2024
I just spend my free time to make it much better based on your feedback
- Mobile support, tested on my iPhone
- GitHub README added
- Added medium zoom for easier viewing on Mobile
- The error banner makes it more friendly and easy troubleshooting
- Troubleshooting section in README
If you have any idea to make the UX better, please let me know, I'll appreciate it
Feel free to raise an issue on Github to keep track progress, it helps open source a lot, or you can DM on x.com/duc__an anytime
I've heard someone reported that Arc had a similar error
In my understanding, It'll possible if the model's author build to https://onnxruntime.ai ONNX Runtime. And maybe the downside is user will need to download ton of data to their device, currently it's ~100-200mb
Yeah I think it's because the quanlity of the model, hopefully we will have better quanlity in near future. I will see if anything I can do with the settings
Will try to the deps simpler later, after all this is about a little time of work
Can you try to go https://pmndrs.github.io/detect-gpu/ and pass the result here
PS: WebGPU is the future