LoRA training cost 500 BUZZ. If you want more LoRAs like that, and more LoRAs trained on CivitAI, please give me BUZZ (or give me your reactions and posts; every your reaction under my images give me 2 BUZZ, every your image-post under my models give me 50 BUZZ).LoRA for SD1.5 trained with CivitAI on 120 (60 originals + 60 mirrored) 680x680 surrealistic mostly female (sometimes doll, android, unisex) portraits in style of Naoto Hattori with manually fixed BLIP2 captions.Training values (all default except resolution): { "unetLR": 0.0005, "clipSkip": 1, "loraType": "lora", "keepTokens": 0, "networkDim": 32, "numRepeats": 2, "resolution": 680, "lrScheduler": "cosine_with_restarts", "minSnrGamma": 5, "targetSteps": 400, "enableBucket": true, "networkAlpha": 16, "optimizerArgs": "weight_decay=0.1", "optimizerType": "AdamW8Bit", "textEncoderLR": 0.00005, "maxTrainEpochs": 10, "shuffleCaption": false, "trainBatchSize": 6, "flipAugmentation": false, "lrSchedulerNumCycles": 3 }Recommended LoRA value between: 0.15 and 1.15With very low value you will get just bigger eyes, longer eyelashes and some acrylic painting vibes.With middle value you will get more general surrealistic art.With highest value you will get more special Naoto Hattori style.Main trigger word: AIDA_NH_humansMost common main trigger word usage: "portrait by AIDA_NH_humans", "painting in style of AIDA_NH_humans", "3D artwork in style of AIDA_NH_humans". It's OK to use trigger word several times in one prompt.Also LoRA should understand:<ol><li>Several tips of backgrounds/environments: "black background, simple background, isolated on black" OR "black background, starry sky" OR "surrealistic landscape, grassy area on the foreground and mountains on the background" OR "sky".</li><li>Difference between open and closed eyes: "open eyes, big eyes with elegant eyelashes" OR "closed eyes with long eyelashes, sleeping, in a dream".</li><li>Difference between cuteness and doom: "pretty face" (for cute portraits) OR "dead woman" (for horrifying portraits).</li><li>Special tags phrases: "liquid flash" (for flesh or hair acting like a liquid, unfortunately mistake in word 'flAsh' is already trained into model), "head flying in the sky" (for head without a body, usually for sky and landscape background), "head flying in the void" (for head without a body, usually for black background), "skin like a paper, skin like a bark, skin turns into ribbons and paper cuts" (for most common futures of Naoto Hattori style)</li></ol>

Files with SHA256: 15e6caa91e9e4ad7ce44799ea745e508921bbe9bf841e7059b2a028419de287b