Elen

UserWarning: The parameter 'pretrained' is deprecated since 0.13

3

I am getting this error/warning every time I run the script. Some help please? C:\Users\xxxxx\anaconda3\envs\GPEN\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please...

### Is there an existing issue for this? - [X] I have searched the existing issues ### Contact Details _No response_ ### What should this feature add? There is a...

[Bug]: torch.cuda.OutOfMemoryError: HIP out of memory. When training embeddings

9

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What happened? Im trying to train a embedding...

Hi, Could you convert it to diffuser?

AssertionError: BNB bad weight without parent layer! BNB bad weight without parent layer!

12

Using the latest commit 2f0555f7dc3f2d06b3a3cc238a4fa2b72e11e28d I get this error when I use a Lora. Using either of these two modelsl: flux1-dev-bnb-nf4-v2 and flux-dev-Q8_0.ggguf ``` Patching LoRAs: 0%| | 0/304 [00:00

FLUX - NF4 uses a lot of RAM and VRAM when a LORA is being used.

23

For some reason dev fp8 works better than nf4 when I use lora, Nf4 just use a lot of vram and ram making the generation speed absurdly slow. With dev...

latest flux branch commit not working for me [CUDA_PATH is set but CUDA wasnt able to be loaded]

1

`2024-09-01 19:45:47.0951724 [E:onnxruntime:Default, provider_bridge_ort.cc:1548 onnxruntime::TryGetProviderInfo_CUDA] D:\a\_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1209 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "F:\flux\venv\lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll" *************** EP Error *************** EP Error...