Greatly improved TEXT + Detail (as CLIP-L for Flux.1)

Add HuggingFace format full model + text encoder only

Added Smooth-GmP - best fine-tune yet! ✨

Add new #1 top-performing smooth-GmP model

ViT-L Text Encoder "same as HF / used in SDXL"

Added .safetensors and full model object pickle

Update README.md

Upload ViT-L-14-GmP-ft-state_dict.pt

Update README.md

initial commit