[QUESTION] possibility to use custom model for clip-l, clip-vision,llava-llama etc.....also in safetensors format?

Is it possible to add a patch in the .py to point to other repo other than [https://huggingface.co/hunyuanvideo-community/HunyuanVideo](url), or load custom safetensors?

The issue does not name a file or test; start by locating the Python code that points to the HunyuanVideo repository and inspect how model files are loaded. Determine the requirements for selecting another repository and loading custom safetensors, then document or implement the agreed behavior and verify it with a custom model.

Written by the indexing model from the issue text.