<h1 id="suliavtuber-style-f0jvnamam">Suliavtuber Style</h1>Reviews are very appreciated and show me you enjoy my work, keeping me motivated in releasing more Models in the future! Would love to see the community create images with my work.Because of the low Dataset on danbooru the base Illustrious Models can't really do this artists style very well. You can see a comparison between just the tag itself and the influence with the LoRA <a target="_blank" rel="ugc" href="https://i.imgur.com/UsJhBq8.jpeg">here</a>. There is a big enough difference and newly achieved accuracy that validates the style as a LoRA.Best Results are at 1 weight &amp; using the trigger word:<pre><code>suliavtuber</code></pre><h2 id="v1.0-(noobai-eps)-jbimau4dj">v1.0 (NoobAI EPS)</h2>Trained on the base <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">NoobAI 1.1 EPS Version</a> model for compatibility with all other NoobAI models.All preview images are created using the <a target="_blank" rel="ugc" href="https://civarchive.com/models/913998?modelVersionId=1122850">NoobAICyberFix 3.0</a> Checkpoint.The settings used to create the images were:<pre><code>Steps: 30
CFG: 7
Sampler: Eular
Scheduler: Normal
Denoise: 1</code></pre><h2 id="v1.0-(il)-nnyivaliz">v1.0 (IL)</h2>Trained on the base <a target="_blank" rel="ugc" href="https://civarchive.com/models/1232765/illustrious-xl-10">Illustrious XL 1.0</a> model for compatibility with all other Illustrious models.All preview images are created using the <a target="_blank" rel="ugc" href="https://civarchive.com/models/140272?modelVersionId=1411148">Hassaku XL v2</a> Checkpoint.The settings used to create the images were:<pre><code>Steps: 30
CFG: 5
Sampler: Eular
Scheduler: Normal
Denoise: 1</code></pre>All images were upscaled using the <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-Remacri">Remacri-4x Model</a>. All images were generated using my ComfyUI workflow that you can find <a rel="ugc" href="https://civarchive.com/models/1297813/comfyui-detaileradetailer-all-in-one-illustrious-pony-sdxl">here</a>, attached to preview images or in the suggested resources. This includes a Detailer that automatically inpaints body parts like eyes, lips, hands etc. So if your results do not match mine it's probably because of this. I recommend using the workflow which is also attached to every image.

suliavtuber Style [NoobAI & Illustrious]

This new noobAI version is more accurately depicting the actual artists style. It was trained on 1024x1024 resolution instead of 512x512 and is doing way better with anotomy, especially hands. The preview images were all generated using the same prompts as the IL version.If you prefer the heavier stylized artstyle of the first(IL) version, you can keep using that for NoobAI Checkpoints as well. Otherwise you can also increase the strength of the LoRA to 1.2-1.4 or use a more saturated stylized checkpoint like <a target="_blank" rel="ugc" href="https://civitai.com/models/140272?modelVersionId=1411148">Hassaku</a>.

Files with SHA256: 1c27c0fc646ef5d4cdf47929c88dd70875d41ba129fedc3d2ced02b82cf2e631