03/12/2025
added a legacy LoRa (Areola Flux Mary/aka Mar_eola Flux)
03/07/25
Added v3, saggy, v2 and v1 were burnt out - v3 hit the spot I was looking for.
Added MetArt_tits - enjoy
03/03/25
Added v3, large, v2 was good, but kept it local.
Model Training Summary
Dataset: Trained on over 40 close-up images of large areolas, sourced from various locations (first round).
Captioning: Captions were generated using Koyha_SS with GIT captioning.
Training: Conducted on Civit's onsite trainer, primarily using default settings, targeting approximately 2,000 steps.
Training Configuration:
{ "engine": "kohya", "unetLR": 0.0005, "clipSkip": 1, "loraType": "lora", "keepTokens": 0, "networkDim": 2, "numRepeats": 20, "resolution": 768, "lrScheduler": "cosine_with_restarts", "minSnrGamma": 5, "noiseOffset": 0.1, "targetSteps": 2025, "enableBucket": true, "networkAlpha": 16, "optimizerType": "AdamW8Bit", "textEncoderLR": 0, "maxTrainEpochs": 5, "shuffleCaption": false, "trainBatchSize": 4, "flipAugmentation": false, "lrSchedulerNumCycles": 3 }
Notes:
A lower weight was used to help the model generalize beyond close-up images. Inpainting wasn’t specifically tested, but previous LoRas have handled it well, so feel free to try it out and share your feedback or thoughts.
Support:
Buzz is nice, or a like.. or a post using the model...
Next Steps:
Version 2 is currently in progress as of August 23, 2024.
09/18/24
figured out how to add versions!!!
Description
Areola Flux - Large v3
Works with SOME character LoRas - lower weight on the character
I use mostly for inpainting/img2img - see examples before CIVITAI takes them down. (most likely)
FAQ
Comments (6)
I like v2, what's the difference between that and v3? And no triggers this time around?
Im having some trouble uploading models to civitai lately, keep getting 401, 404 errors as I am editing the model, this one does have trigger words, but not 100% needed. Biggest difference is the dataset/dim weight
and CIVITAI Freezes when I comment... sweet website!
I noticed ar3ol4, any other triggers you recommend trying?
@Kiefstorm what do you use to generate (forge, comfy, etc..) I use forge, if you view the lora details it shows all the captured tags.. (not sure if it does that in other UIs) so whatever it picked from florence. I added "A womans breasts, ar3ol4", and that was it.. so it picked up womans, breasts, breast.. but "ar3ol4" was the main. Hope that helps.
@rickets_xxx no it doesn't do that in ComfyUI by default but now that you mention it I've seen a Node that gives Lora info though including tags. I'll add that to my workflows