03/12/2025<ul><li>added a legacy LoRa (Areola Flux Mary/aka Mar_eola Flux)</li></ul>03/07/25Added v3, saggy, v2 and v1 were burnt out - v3 hit the spot I was looking for. Added MetArt_tits - enjoy03/03/25 Added v3, large, v2 was good, but kept it local.<h3 id="model-training-summary-w8ag82cth">Model Training Summary</h3>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!!!

Areola Flux

V1 - works "ok" with other character LoRas - still testing. - depending on model, 20-40 steps (f8) - CFG between 5-7 Large Areola

Files with SHA256: f78ea2a96f5f254a6a143c136253923a1b8c08154f301868102fb5f9ad4a2188