Sign In

EYE DETAIL FLUX LORA (& INPAINT)

899
7.3k
1m
283
Verified:
SafeTensor
Type
LoRA
Stats
1,852
5,204
Reviews
Published
Oct 28, 2024
Base Model
Flux.1 D
Trigger Words
detailed eyes
Hash
AutoV2
3107D1FFA5
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

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.