<h1 id="heading-85">Hinata Natsumi from Keroro Gunsou / ケロロ軍曹</h1>This is my second release of a LoRA model. Please feel free to rate the model or share your creations with it. I'd be thrilled to see your works. If you find it useful, consider showing your appreciation by <a target="_blank" rel="ugc" href="https://ko-fi.com/allureai">buying me a coffee</a>.<ul><li>Weight: between 0.8 to 1.0</li><li>Trigger Word: hinata_natsumi</li><li>Additional Prompts: red eyes, red hair, twintails</li></ul>Suggested Hires.fix configuration:<ul><li>Upscaler (For Anime Models): R-ESRGAN 4x+ Anime6B</li><li>Upscaler (For PhotoReal Models): R-ESRGAN 4x+</li><li>Hires steps: between 10 to 20</li><li>Denoising strength: between 0.15 to 0.25</li></ul>One of my favourite tasks is transitioning characters from anime to photorealistic renditions or vice versa. The results are always unpredictable, and the anticipation until the final render is exhilarating. This LoRA model performs well in photorealistic settings too.Your comments or suggestions are not only welcome but can significantly improve the quality of my models. They also motivate me to create more LoRA models. Feel free to connect with me on my <a target="_blank" rel="ugc" href="https://discord.gg/9U3fV2Y3">Discord channel</a>.V2 was trained on the AnyLoRA base model with a dataset comprised of 87 images.The compatibility of this LoRA model has been tested and work well with the following base models:<h3 id="heading-86">Anime models:</h3><ul><li>MeinaMix V11</li><li>Perfect World V4</li></ul><h3 id="heading-87">Photorealistic models:</h3><ul><li>AbsoluteReality V1</li><li>CyberRealistic V3.2</li></ul>All demonstration images showcased are randomly selected, not handpicked for optimal results.

Files with SHA256: f9df91e3f6480c391e52014b871f2b7c4f4c659d7771d0e7be29a0f6d1c15fe2