No trigger word needed for the style, words like "bimbofication, multiple views, transformation" and "monsterification" are useful for depicting those concepts.Training data: <a target="_blank" rel="ugc" href="https://files.catbox.moe/mhfm2g.zip">https://files.catbox.moe/mhfm2g.zip</a>Please support the artist! Links to their Patreon and Twitter below.<a target="_blank" rel="ugc" href="http://patreon.com/wrenzephyr2">http://patreon.com/wrenzephyr2</a><a target="_blank" rel="ugc" href="https://twitter.com/WrenZephyr">https://twitter.com/WrenZephyr</a>

WrenZephyr Style

Illustrious version created by me. Slightly different dataset, similar tagging (added "furrification").Training data: <a target="_blank" rel="ugc" href="https://files.catbox.moe/nqbsb4.zip">https://files.catbox.moe/nqbsb4.zip</a>{ "engine": "kohya", "unetLR": 0.0005, "clipSkip": 1, "loraType": "lora", "keepTokens": 1, "networkDim": 32, "numRepeats": 2, "resolution": 1024, "lrScheduler": "cosine", "minSnrGamma": 5, "noiseOffset": 0.1, "targetSteps": 1473, "enableBucket": true, "networkAlpha": 32, "optimizerType": "Prodigy", "textEncoderLR": 0.00005, "maxTrainEpochs": 19, "shuffleCaption": false, "trainBatchSize": 4, "flipAugmentation": false, "lrSchedulerNumCycles": 3}

Files with SHA256: b3f835aaebc3a4ebf2a3ceca60aba2e8a9bc0d94a59354a55dc746fd0d091df4