From now on all future versions will be named after their base model, for example if I train with the YAAI dataset on Pony V6 the version of the model will be named "PonyV6", this is to clear up confusion since I am planning on training on a lot of other base models. The original V1 and V2 models will remain with their original names. I do want to make it clear that every new version that I make is not supposed to be "better" than the old ones, they're just different, which is why I am training on different base models each time, the only constant is the dataset. Each model is trained on a hand picked dataset of art that I liked, results should generally speaking be a little more stylized than their original base, with some improvements on creativity as well.Here's the V2 (WAI-NSFW V15 base used) model on <a target="_blank" rel="ugc" href="https://tensor.art/models/924979416080060628">tensor</a> Comparison of YAAI v2.0 and WAI v15: <a target="_blank" rel="ugc" href="https://imgsli.com/NDE4OTg5">https://imgsli.com/NDE4OTg5</a>Comparison of YAAI v1.0 and WAI v14: <a target="_blank" rel="ugc" href="https://imgsli.com/NDA5NzU4">https://imgsli.com/NDA5NzU4</a><h3 id="recommended-settings:">Recommended settings:</h3>Steps:: 15-30CFG scale: 5-7Sampler: EulerUse size larger than 1024x1024 for the original dimensions<h3 id="recommended-upscale-settings:">Recommended upscale settings:</h3>Hires upscale: 1.5Hires steps: 20Denoising strength: 0.35~0.5Hires upscaler: <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-realesrgan-x4plus-anime-6b"><span style="background-color:rgb(26, 27, 30);color:rgb(255, 255, 255);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">R-ESRGAN 4x+ Anime6B</a>All the preview images have the workflow attached, it automatically calculates a 1.5x resolution for you so you don't have to change multiple fields each time you want to change resolution.Everything is included in the checkpoint (vae, text encoders, unet)<h3 id="recommended-prompts:">Recommended prompts:</h3>Positive Prompt<pre><code>masterpiece, best quality, amazing quality, absurdres</code></pre>Negative Prompt<pre><code>bad quality, worst quality, worst detail, sketch, censor, watermark, signature, text, multiple_poses, multiple_scenes, speech_bubble, patreon_username, multiple_images, multiple_angles, bad_hands, wrong_hand, bad_anatomy, extra_fingers, extra_digits </code></pre> Basically all characters in the WAI-NSFW model should work here too, you can check all the characters available here: <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/flagrantia/character_select_saa">https://huggingface.co/spaces/flagrantia/character_select_saa</a>Of course due to the nature of full fine tuning some characters might be impossible to be generated anymore, but from my testing all characters that I tried worked fine.

YAAI (Yet Another Anime Illustrious ᵐᵒᵈᵉˡ) | Full fine tune based on WAI-NSFW

yaaiYetAnotherAnimeIllustrious_v20.safetensors

v2.0

v1.0

This model is basically what I would've wanted <a target="_blank" rel="ugc" href="https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl">WAI-NSFW</a> to look like, art style is modified to my preference, it is a bit more messy with more textured line work. Some features are a bit exaggerated as well, breasts for example are usually bigger. The model was trained on a hand picked dataset of art that I liked.Here's the model on <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/1899729/yaai-yet-another-anime-illustrious-or-full-fine-tune-based-on-wai-nsfw">civitai</a>-Update-v2.0 has been released with the following improvements:<ul><li>trained on the new WAI-NSFW v15 as base</li><li>new settings used that capture small details better</li></ul>v2.0 has been trained for longer than the previous version, so it is less subtle. Let me know if you like this change or not.Comparison of YAAI v2.0 and WAI v15: <a target="_blank" rel="noopener noreferrer nofollow" href="https://imgsli.com/NDE4OTg5">https://imgsli.com/NDE4OTg5</a>Comparison of YAAI v1.0 and WAI v14: <a target="_blank" rel="noopener noreferrer nofollow" href="https://imgsli.com/NDA5NzU4">https://imgsli.com/NDA5NzU4</a>Recommended settings:Steps:: 15-30CFG scale: 5-7Sampler: EulerUse size larger than 1024x1024 for the original dimensionsRecommended upscale settings:Hires upscale: 1.5Hires steps: 20Denoising strength: 0.35~0.5Hires upscaler: <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-realesrgan-x4plus-anime-6b">R-ESRGAN 4x+ Anime6B</a>All the preview images have the workflow attached, it automatically calculates a 1.5x resolution for you so you don't have to change multiple fields each time you want to change resolution.Everything is included in the checkpoint (vae, text encoders, unet)Recommended prompts:Positive Prompt:masterpiece, best quality, amazing quality, absurdresNegative Prompt:bad quality, worst quality, worst detail, sketch, censor, watermark, signature, textBasically all characters in the WAI-NSFW model should work here too, you can check all the characters available here: <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/spaces/flagrantia/character_select_saa">https://huggingface.co/spaces/flagrantia/character_select_saa</a>Of course due to the nature of full fine tuning some characters might be impossible to be generated anymore, but from my testing all characters that I tried worked fine.

Files with SHA256: ee543de21469f961d4b7e20b91a4f0d7d0c5d1a9582efd7fd90c106edda3a8cb