can you add adefiniable path to embedding checkpoints so we can use finetuned models ?

python scripts/txt2img.py --ddim_eta 0.0
--n_samples 8
--n_iter 2
--scale 10.0
--ddim_steps 50
--embedding_path /path/to/logs/trained_model/checkpoints/embeddings_gs-5049.pt
--ckpt_path /path/to/pretrained/model.ckpt
--prompt "a photo of *

i tried to place model.embedding_manager.load(opt.embedding_path) in original gui script but no success, it errors out when i prompt - newthing*

Its from this inversion repository to finetune weights
https://github.com/nicolai256/Stable-textual-inversion_win