Sign In

EYE DETAIL FLUX LORA (& INPAINT)

1k
8.5k
1.1m
339
Verified:
SafeTensor
Type
LoRA
Stats
5,906
1,096,316
144.2k
Reviews
Published
Jan 12, 2024
Base Model
SDXL 1.0
Training
Steps: 1,500
Epochs: 10
Trigger Words
detailed_eye_model
Hash
AutoV2
09F6B6B1DC

For the example photos, 2 do not have Adetailer. The zoomed in photo does have Adetailer present for mediapipe_face_mesh_eyes_only.

Really does well at weight "2". This will cause your image to zoom in though, so play with the weight. I have found that INPAINTING the eyes will work better if you are worried about the zoom in.

Highly recommend .7 denoising, but you can play and find what best works for you.

I HIGHLY recommend using Adetailer to further the process.