This model was trained using image from fishine / hirame / ireading62.I made a few iterations until I got a stable model that had the intended look. The model used for training was pony v6, so models derived from it should also work.Note: I like the style when using <code>halftone, hatching \(texture\), jaggy lines</code>Changelog:<ul><li>v12: first model published (12th iteration I've trained)</li><li>v14: removed some images which were causing some instability; increased gradient accumulation</li><li>v15: relabeled images with wd1.4 tagger v3, using 0.35 threshold; seems a bit less stable, but more flexible</li><li>v22: recreated the dataset (total 121 images); some images will need manual labeling since the model quality seems limited by the wd1.4 tagger (v2/v3)</li></ul>

fishine / hirame / ireading62 style LoRA (PonyXL)

Trained with 16 gradient accumulation steps, for ~192 epochs on 49 images (labeled by wd14 tagger)

fishine_v12.safetensors

v22m

THIS IS A REPRINT!Go to original author to check their other models or to support them. <hr /> This model was trained using image from fishine / hirame / ireading62.I made a few iterations until I got a stable model that had the intended look. The model used for training was pony v6, so models derived from it should also work.Note: I like the style when using <code>halftone, hatching \(texture\), jaggy lines</code>Changelog:<ul><li>v12: first model published (12th iteration I've trained)</li><li>v14: removed some images which were causing some instability; increased gradient accumulation</li><li>v15: relabeled images with wd1.4 tagger v3, using 0.35 threshold; seems a bit less stable, but more flexible</li><li>v22: recreated the dataset (total 121 images); some images will need manual labeling since the model quality seems limited by the wd1.4 tagger (v2/v3)</li></ul>

Files with SHA256: ebd0959db9104a5ce57ff72b17bb81f2c5f866f26d83dbcf2d252171d34e7cb4