Credit goes to @Minthybasis for his <a target="_blank" rel="ugc" href="https://civarchive.com/models/282341/4th-tail-animehentai">finetune</a> and the <a target="_blank" rel="ugc" href="https://civarchive.com/models/312010/4th-tail-lora-extract">extract</a>, and authors of the original models.I merged the extract into some models and found that it improves the image &amp; contrast.More tags from danbooru like artists, characters, styles, and general concepts are added.Adding the lyco will work using <a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Inspire-Pack">this node</a>, <a target="_blank" rel="ugc" href="https://files.catbox.moe/v0ysgs.png">these settings</a>.Using a "Load Lora" node will not work since it's placing the data over all the blocks.Writing to the output blocks using the lycoris preset, the data contained within the extract does not overwrite Pony's existing data of anatomy and composition, instead adding it to blocks outside of them. But it does improve the anatomy in my testing.<a target="_blank" rel="ugc" href="https://mega.nz/folder/5KJFDThQ#C-W-c_Qq86TojBXFMlXYwQ">Here is a study</a> of the artists that may be detected<a target="_blank" rel="ugc" href="https://files.catbox.moe/97r34f.txt">Some characters sorted alphabetically.</a> Use copyright and appearance tags

4thLyco Merges

<a target="_blank" rel="ugc" href="https://huggingface.co/LMFResearchSociety/CheckpointArchive/blob/main/anon/0.5(0.8(0.8(ponyDiffusionV6XL_v6)%20%2B%200.2(animeconfettitunexl_con5tixl))%20%2B%200.2(js2prony_v10))%20%2B%200.5(autismmixPony).safetensors">original model</a>

Files with SHA256: ec22f1470eeba0323a5ae96e6edb15dfea2a7b1ccde3ee37c4ec2d3095d8609d