I need some help. I trained a flux LoRA
I need some help. I trained a flux LoRA with highest training.
So the text encoder was tuned as well.
When i place the text encoder in the SwarmUI/Models/clip path. It re-downloads with the name t5xxl_enconly.
I have this t5xxl_fp16.safetensors with me which presumably got tuned.
Everything else is fine. I am doing something wrong here with t5.
I donloaded models from this HF Repo. "OwlMaster/FLUX_LoRA_Train"
Any help would be great. I am on a cloud VM and banging my head for this.
4 Replies
Any help on this would be really appreciated.
you need to rename to same name as swarmui uses :d
and overwrite swarmui downloaded one
Okay thanks dr.
you are welcome