Nitin Tiwari

@markmcd: Could you please help with this?

@Areej25890, check if the `train.txt` file is empty or not. If it's empty, then the training probably didn't start; no `.weights` file will be generated thereby.

I'm looking for the same solution. I've fine-tuned the runwayml stable-diffusion-1.5 model on custom dataset and generated the LoRA weights which are of the type .safetensor. What are the steps...

Hi @khanhlvg, @yichunk, Can you please help with this? How do we convert the safetensor file to .task file that is compatible with MediaPipe?


Update: I tried to run the app on a different mobile phone (OnePlus Nord CE3 Lite) - Android 13 and now I get a different error. E0000 00:00:1705733677.683472 7245 diffuser_gpu.cc:88]...

> @NSTiwari on your steps above you have not mentioned converting the standalone model with the [convert.py](https://github.com/googlesamples/mediapipe/tree/main/tools/image_generator_converter) script. Have you done this step? @farmaker47 Yes, this step was done. Here...

@khanhlvg: Could you please help with this issue?

@SimrnGupta, when I try to load the PascalVOC dataset, it gives an error that says, "Image format not JPEG", although all the images are of the said format. May be...

@chongkuiqi could you please share the build files generated after running `prepare_libs.sh` for Llama3? Let me try.