from pixiv HIKAv2.0 update : no difference in datasets, but use text encoder for general use, and increase total learning stepsv3.0 : training using only his latest images, dataset does not overlap with v2.0v2.0 vpred update : I trained it on the v2.0 dataset (500 images), using noobai vpred as the base model. It's an unrefined dataset crawled from Pixiv, so rather than converging on a single art style, it feels more like a hodgepodge. Anyway ¯\_(ツ)_/¯v3.0 vpred update : I trained this version by adding a bit more data to the existing v3.0 dataset (150 images). As an experiment, I tested training at 1280x1280 resolution. The sample images were also all generated at resolutions of 1024x1024 or higher.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2b6cb80c-28e9-4816-b6c5-6dbf7403479d/width=525/2b6cb80c-28e9-4816-b6c5-6dbf7403479d.jpeg" />( v3.0 IL | v3.0 vpred )It seems to maintain the original body proportions 'slightly' better at high resolutions. It's not a dramatic difference, but it gave me an interesting idea to make multiple 1280-resolution LoRAs and merge them into a model.

HIKA / Style

HIKA4-15.safetensors

Files with SHA256: 40fc958552d898b470490f7bc3c358a6a3cc990337fd9de1c9f40f3bed50c52f