<a target="_blank" rel="ugc" href="https://github.com/deepghs/waifuc/tree/main">https://github.com/deepghs/waifuc/tree/main</a>The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently crawl and process over 3000 training images within a span of 2 hours. Training the character "Lora" on this extensive dataset yields significant performance advantages compared to situations with limited data availability.↑ Translation from gpt.Trigger Words :FUUKA \(BLUE ARCHIVE\)train:158Imagerecommand use model: Kohaku_XL <a target="_blank" rel="ugc" href="https://civarchive.com/models/162577/kohaku-xl-beta">https://civarchive.com/models/162577/kohaku-xl-beta</a>weight: 0.8~1if not halo,please add “halo" to prompt

Files with SHA256: db0b41b67f6c817a206c2d07f9723f85d79e17fbef266346969ecf1afba8763c