kotaxyz

it worked thanks alot man yes my card supports fp16 , i didnt notice mixed precision line

> can yall help me fix my problem? what is it

it fixed the issue upove now it progresses and give another issue `100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [01:01

i disabled the gradients and it changed the error to be this `================================================================================ CUDA SETUP: Loading binary I:\dreambooth\koya\kohya_ss\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda116.dll... use 8-bit Adam optimizer running training / 学習開始 num train images *...

yes it worked for me too thanks buddy

> also i turned off 8bit adam and am getting the same error disable gradient checkpoint in advanced settings , make sure to choose fp16 in mixed precision and save...

if the error is still happening just comment the error you get it may be different from mine in some lines this will help

i get this error when i try to do style transfer to any bvh file except the files in xia_test (Deep-motion-editing) C:\Users\Genesis\github\deep-motion-editing>python style_transfer/test.py --content_src style_transfer/data/xia_test/bassball.bvh --style_src style_transfer/data/xia_test/angry_13_000.bvh --output_dir style_transfer/demo_results/demo_3d_2 C:\Users\Genesis\github\deep-motion-editing\style_transfer\probe\..\pretrained...

https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation/tree/main/ckpt

activate the conda environment then write these commands and make sure you change the microsoft visual studio version with the one you have ,you can search for the vcvars32.bat and...