This Adetailer model will segment speech bubbles, text and watermarks commonly found in training data. Trained this so I could eventually automatically clean images in a dataset. Only tested on Comfy, but should work on other webUIs too. This is a WIP, and I have many things in mind on which could be improved:<a rel="ugc" href="https://civarchive.com/articles/7364">Instructions/Workflow</a>Known issues:<ul><li>make sure you don't set minimum confidence too low, or else undesired objects will be segmented</li><li>can misidentify watermarks for text, speech bubbles for logos etc. but this should not matter since they are segmented anyway</li><li>Some text that is transparent/partially hidden won't be identified</li><li>Trained primarily on NSFW images, may not work too well with comics, images with large/strange fonts etc.</li></ul>

Adetailer for Text / Speech bubbles / Watermarks | Anime/Furry

Increased dataset size, better annotation

Files with SHA256: b601a1d8850f6df688a558c8a53a37399d938f241695b1dae9b004be8ccdce3f