This Lora model was trained on Joseph Ducreux’s Self-Portraits (ca. 1790) using images in the Public Domain. The images were cropped, upscaled and denoise before training. v21-DB2 no captions, pure style model designed for Stacking. v21-style - trained on dataset sharing the same name, BLIP2 captions (prompting captions produces close variation on ground truth) Danger Helpers here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/20517/danger-zoo-johnsons-negative-embeddings-helper-collection">https://civarchive.com/models/20517/danger-zoo-johnsons-negative-embeddings-helper-collection</a>

Files with SHA256: 37b0da2cabd2c5a1cdb82aa8d9fb3c8b77d428d207c143f5623b4946b5f8972e