IM SURPRISED THIS NEEDS TO BE SAID, BUT THE MODEL NEEDS DANBOORU STYLE PROMPTING. IT IS BASED ON ILLUSTRIOUS SO IF YOU DON'T USE DANBOORU PROMPTING YOU WILL GET BAD RESULTS!v3.0 is now available! This release delivers the following improvements:<ul><li>This release brings the detail and realism enhancements of v2.5 while keeping the diversity of v2.0</li></ul>v3.0 took a while because I was experimenting with making it truly photorealistic, but honestly while that IS possible, it ends up making the model too stiff. What I mean by this is that it first of all stops re-creating characters properly, so for example if you try to generate Sakura from naruto you will end up getting a girl with pink hair, but her face will look nothing like Sakura. On top of that prompt adherence suffers. Both of these symptoms can be seen in other models which are pretty photorealistic (specifically talking about illustrious based models ofc). I decided to keep my model as realistic as possible while still being able to be flexible, so my model can still re-create most characters with 200+ posts on danbooru AND it is still flexible enough to do generations with multiple characters or weird poses etc.Enjoy v3.0! :)Little tip that should improve character likeness in some cases:If a character's tag on danbooru is listed with parenthesis you should add a backslash before the first and last parenthesis. So for example "raven_(dc)" becomes -&gt; "raven_\(dc\)".<hr />The point of this model is to have all the characters built into <a target="_blank" rel="ugc" href="https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl">WAI-NSFW</a> (full credit to <a target="_blank" rel="ugc" href="https://civarchive.com/user/WAI0731">WAI0731 </a>for creating this incredible model), while having a more realistic look.<h3 id="!!!-important-note-!!!">!!! Important note !!!</h3>Existing Loras won't work with this model since it is a fine tune, not a merge. It's possible that some loras might work, but most of them won't.Popular loras that I have tested and confirmed that work well with my model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/341353/expressiveh-hentai-lora-style?modelVersionId=382152">ExpressiveH</a>,<a target="_blank" rel="ugc" href="https://civarchive.com/models/341353/expressiveh-hentai-lora-style?modelVersionId=382152"> </a><a target="_blank" rel="ugc" href="https://civarchive.com/models/122359/detail-tweaker-xl?modelVersionId=135867">Detail Tweaker XL</a>THE RECOMMENDATIONS BELLOW APPLY FOR ALL VERSIONS<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/2x-NomosUni-span-multijpg-ldl">2xNomosUni_span_multijpg_ldl </a>(I tested a bunch of upscalers and this seems to work quite well for more realistic images, and it is pretty fast). If you want the best possible quality you can use <a rel="ugc" href="https://openmodeldb.info/models/4x-RealWebPhoto-v4-drct-l">4xRealWebPhoto_v4_drct-l</a>, just keep in mind that it is a lot slower.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>photorealistic, photograph, realistic, masterpiece, best quality, amazing quality, absurdres, detailed_skin</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.Old version update logs:v2.0 is now available! This release delivers the following improvements:<ul><li>Slightly enhanced stability and prompt adherence across all outputs</li><li>Expanded dataset with ~3x more training data (compared to v1.0), this helps diversify results</li><li>1536px training, yields more detail than previous versions</li><li>Facial expressions have been improved, with previous versions smirks/slight smiles and other facial expressions often looked creepy, this is now mostly fixed, all facial expressions should look better (still possible to get bad results but a lot more rare now)</li></ul> v1.0 is now available! This release delivers significant improvements:<ul><li>Enhanced stability and realism across all outputs</li><li>Reduced CGI/plasticky look (still happens, but is more rare)</li><li>Expanded dataset with ~2x more training data</li><li>Multi-resolution training (1024px and 1280px vs 1024px only in v0.1)</li></ul>

YARI (Yet Another Realistic Illustrious ᵐᵒᵈᵉˡ) | Full fine tune based on WAI-NSFW

YARI_v3.0.safetensors

YARI (Yet Another Realistic Illustrious ᵐᵒᵈᵉˡ)

Files with SHA256: 6f1b463b9addcacd68db9226f079a28599c4ffe9781db05da7d62e37c167d3be