[Feature Request] ONNX support

[FNsi]

In compact structure (model size 256k~4m) that would be a runtime effect base on DirectMl

Am I so greedy?😂

[HIllya51]

Kindly note that only DirectML backend is supported by non-NVIDIA graphics cards. Can you provide the logs to help diagnose the problem?

logs.zip

[Blinue]

It’s likely due to OOM; I suspect the integrated graphics card doesn’t have sufficient resources to perform the inference. Can you share the ONNX file you’re using?

[HIllya51]

It’s likely due to OOM; I suspect the integrated graphics card doesn’t have sufficient resources to perform the inference. Can you share the ONNX file you’re using?

I just use the 2x_AnimeJaNai_HD_V3_UltraCompact_425k-fp16.onnx

[Blinue]

I just use the 2x_AnimeJaNai_HD_V3_UltraCompact_425k-fp16.onnx

For effective inference on the UC model, a minimum of a 3060 GPU is essential. While it might be feasible to run much smaller models on integrated graphics cards, it doesn’t make much sense to do so: for tiny models, HLSL is significantly faster.

[hooke007]

Does the ONNX version not support Integrated graphics? The screen will go black on the AMD R6-6600H CPU...

If you only want to verify if ONNX would work. I only suggest use "tiny" model on IGPU(i.e. https://github.com/Blinue/Magpie/issues/847#issuecomment-1988711628)

[HIllya51]

I just use the 2x_AnimeJaNai_HD_V3_UltraCompact_425k-fp16.onnx

For effective inference on the UC model, a minimum of a 3060 GPU is essential. While it might be feasible to run much smaller models on integrated graphics cards, it doesn’t make much sense to do so: for tiny models, HLSL is significantly faster.

Does the ONNX version not support Integrated graphics? The screen will go black on the AMD R6-6600H CPU...

If you only want to verify if ONNX would work. I only suggest use "tiny" model on IGPU(i.e. #847 (comment))

I conducted some tests again and found that it can scale certain windows correctly (nodepad, calculator, window terminal), but it may black out for certain windows (explorer, some games)， so it may not be an error caused by ONNX, but rather a bug in window capture

[Blinue]

I conducted some tests again and found that it can scale certain windows correctly (nodepad, calculator, window terminal), but it may black out for certain windows (explorer, some games)， so it may not be an error caused by ONNX, but rather a bug in window capture

I believe this is related to the window size. Scaling larger windows requires more VRAM, leading to OOM.

[HIllya51]

I conducted some tests again and found that it can scale certain windows correctly (nodepad, calculator, window terminal), but it may black out for certain windows (explorer, some games)， so it may not be an error caused by ONNX, but rather a bug in window capture

I believe this is related to the window size. Scaling larger windows requires more VRAM, leading to OOM.

I have tested it, and for the software I mentioned earlier that can be scaled, no matter how I resize it, it can scale normally. For software that cannot be scaled, no matter how I resize it, it will black screen

[Blinue]

@HIllya51 Could you create an issue for this problem?

[keyrwhf]

Thank you so much! I love this tool. I apologize for my English; it’s not very good. However, I’m facing an issue. I’m using Magpie with Textractor to read a Visual Novel game. In this ONNX preview version, it only supports the graphic capture method; other methods don’t work. Textractor generates an extra window text box that stays “Always on top” to display text. When I use the graphic capture method, the text box disappears. However, the Desktop Duplication method works with Textractor, and the text box doesn’t disappear. Can you please help?

[Blinue]

In the onnx-preview1 version, only Graphics Capture is functional; other capture methods have not been adapted. It's merely a technical preview, so stay tuned for future updates.