Ju Hoon Park
Ju Hoon Park
@nitinmukesh That was a close call😳 thank you sincerely for taking the time to test this with me 🙇♂️ I’ve promptly updated the code based on the guidance you provided....
@nitinmukesh Oh! Thank you very much for helping me notice something I had previously overlooked. 🙇♂️ I tested the loading of the 14B version GGUF model as follows: ```python import...
@nitinmukesh Upon execution, I did not encounter any warnings such as `Some weights of the model checkpoint were not used when initializing WanVACETransformer3DModel: ....` Instead, the following error was raised...
Thank you so much 🙇♂️ I'm truly delighted to hear that everything is loading perfectly! I'm especially thrilled to contribute to diffusers, which I consider a true work of art....
@tolgacangoz I truly appreciate your great work, and apologize for the late response When I tried running the script attached to the message, I encountered the following error at `pipe.enable_model_cpu_offload()`:...
Dear @tolgacangoz I appreciate for your hard work again! While trying to use `pipe.enable_sequential_cpu_offload()` instead of `pipe.enable_model_cpu_offload()`, I encountered an error like below: error stack trace ```text File .../torch/utils/_contextlib.py:120, in...
@tolgacangoz Thanks! I am delighted to help☺️ Have a peaceful day!
@isaacrob-roboflow I believe I've found a fix for this issue. May I open a pull request to propose the change?
@isaacrob-roboflow @hangxu811 I apologize for the delayed response. I encountered the same issue when building from source, so I’m sharing a minimal reproducible example here for reference. minimal code representation...
@isaacrob-roboflow Thank you! I'm delighted to have the opportunity to contribute to rf-detr. I’ll open a PR soon!