Eye Segmentation for ADetailer
Credits to mnemic for this article and Anzhc for this ADetailer model (see for more information)
Installation:
Download the zip archive
Extract the model into your ADetailer model folder
For the WebUIs like Auto1111, Forge and SD.next it should be in models/adetailer
For ComfyUI it should be in models/ultralytics/segm
Start it up (full restart if already had it open) and select the model from the ADetailer tab/node
Tip for WebUI: you can go to WebUI Settings→Adetailer and change the number of models that can be used up to 10, very useful if you want to use more than 2 ADetailer models
If you want to do both eyes in one pass (so you keep consistency in the eyes). In your ADetailer tab, go to Mask preprocessing → Mask merge mode → and select 'Merge'. This will merge the masks and do the inpaint as if it's one mask. Keep in mind this might not be ideal if there are 2 subjects and say 4 eyes. You can mess with settings and maybe do it in some way™️. You'll have to figure that on your own.
Make sure to have correct Detection thresholds/inpaint strength and so on for your images
Generate them eyes!
It detects eyes pretty well. I might work more on this in the future. Please tell me what you think. Thanks! 😊
Description
FAQ
Comments (8)
Lol, thanks for crediting me for face model xd
(P.S. don't you dare to correct spelling of my nickname, i love that everyone spells it wrong)
I actually am working on eye seg model too, just ironing out some inconsistencies on sclera selection
Nice! I do expect more detection models to come out. I am also working on some.
Thanks for sharing, great job!
Thank you! ❤️
for some reasons easy diffusion detect your lora as a virus
Sorry to hear that, also this is not a LORA. The only reason it gets flagged as a 'virus' is because it is not in the .safetensors format, the .pt format is default for ADetailer models and that's the only way to use it as far as I know. You can safely ignore the issue and use it if you like. If in the future a way to convert these to a .safetensors format becomes available I will, but until then this all I can do.
@Pitpe11 There is a script on Hugging Face I used to convert the SD1.5 embeddings to safetensor. So .pt to .safetensor. I have a feeling changing the .pt ADetailer files this way would break things tho..
@lucidzachary473 it will, yes. I've tried a few scripts that supposedly convert but none work for adetailer/yolo models. Maybe one day there will be one.