LarosBell-XL v2 is the next version of LarosBell-XL with great improvements in Anatomy and the style is close to LarosBell in SD 1.5 Model Details:<ul><li>Developed by: [Bell-Fi]</li><li>Model type: Diffusion-based text-to-image generative model</li><li>Model Description: Generate high-quality 3D anime images from textual prompts</li><li>License: <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a></li><li>Merged from models:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-3.1">Animagine XL 3.1</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/140737/albedobase-xl">AlbedobaseXL 2.1</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Raelina/RaemuXL">RaemuXL 3.0</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/267879/pvcxl-v10-lora-for-animaginexl-30-animaginexl-30-base">PVC-XL Lora</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/9409/or-anything-xl">Anything-XL</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/125907?modelVersionId=254091">RealCartoon-XL-v6</a></li></ul></li><li>Huggingface : <a target="_blank" rel="ugc" href="https://huggingface.co/ItsMeBell/LarosBell-XL">ItsMeBell</a> Prompting is a bit different in this model, for optimal results, it's recommended to follow the structured prompt template:<pre><code>1girl/1boy, character name, from what series, everything else in any order.</code></pre>To guide the model towards generating high-aesthetic images, use negative prompts like:<pre><code>normal quality, low quality, worst quality, text, error, missing fingers, extra digit, jpeg artifacts, signature, watermark, username, blurry, artist name</code></pre>For higher quality outcomes, prepend prompts with:<pre><code>1girl/1boy, character name, from what series, everything else in any order, masterpiece, best quality, high quality</code></pre>Multi Aspect Resolution:This model supports generating images at the following dimensions:<pre><code>Dimensions	Aspect Ratio
1024 x 1024	1:1 Square
1152 x 896	9:7
896 x 1152	7:9
1216 x 832	19:13
832 x 1216	13:19
1344 x 768	7:4 Horizontal
768 x 1344	4:7 Vertical
1536 x 640	12:5 Horizontal
640 x 1536	5:12 Vertical</code></pre>Hires.fix Setting <ul><li>Upscaler: <a target="_blank" rel="ugc" href="https://nmkd.de/?esrgan">4x-YandereNeoXL</a></li><li>Hires step: 10-20</li><li>Denoising: 0.2-0.4 or 0.55 for latent upscaler</li></ul>LarosBell-XL now uses the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> inherited from Animagine XL 3.0, compatible with Stable Diffusion models. Key points:<ol><li>Modification Sharing: If you modify LarosBell-XL, you must share both your changes and the original license.</li><li>Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.</li><li>Distribution Terms: Any distribution must be under this license or another with similar rules.</li><li>Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.</li></ol>The choice of this license aims to keep LarosBell-XL open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms.</li></ul>

LarosBell-XL

larosbellXL_v20.safetensors

v2.0

v1.0

LarosBell-XL is a merged model that specializes in generating high-quality 3D anime images from textual prompts. Model Details:<ul><li>Developed by: [Bell-Fi]</li><li>Model type: Diffusion-based text-to-image generative model</li><li>Model Description: Generate high-quality 3D anime images from textual prompts</li><li>License: <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a></li><li>Huggingface : <a target="_blank" rel="ugc" href="https://huggingface.co/ItsMeBell/LarosBell-XL">ItsMeBell</a> Prompting is a bit different in this model, for optimal results, it's recommended to follow the structured prompt template:<pre><code>1girl/1boy, character name, from what series, everything else in any order.</code></pre>To guide the model towards generating high-aesthetic images, use negative prompts like:<pre><code>normal quality, low quality, worst quality, text, error, missing fingers, extra digit, jpeg artifacts, signature, watermark, username, blurry, artist name</code></pre>For higher quality outcomes, prepend prompts with:<pre><code>1girl/1boy, character name, from what series, everything else in any order, masterpiece, best quality, high quality</code></pre>Multi Aspect Resolution:This model supports generating images at the following dimensions:<pre><code>Dimensions	Aspect Ratio
1024 x 1024	1:1 Square
1152 x 896	9:7
896 x 1152	7:9
1216 x 832	19:13
832 x 1216	13:19
1344 x 768	7:4 Horizontal
768 x 1344	4:7 Vertical
1536 x 640	12:5 Horizontal
640 x 1536	5:12 Vertical</code></pre>Hires.fix Setting <ul><li>Upscaler: <a target="_blank" rel="ugc" href="https://nmkd.de/?esrgan">4x-YandereNeoXL</a></li><li>Hires step: 10-20</li><li>Denoising: 0.2-0.4 or 0.55 for latent upscaler</li></ul>LarosBell-XL now uses the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> inherited from Animagine XL 3.0, compatible with Stable Diffusion models. Key points:<ol><li>Modification Sharing: If you modify LarosBell-XL, you must share both your changes and the original license.</li><li>Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.</li><li>Distribution Terms: Any distribution must be under this license or another with similar rules.</li><li>Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.</li></ol>The choice of this license aims to keep LarosBell-XL open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms.</li></ul>

Files with SHA256: baaefca785d8808a6e4e3d6b10687fbcaa40cd6e03a94a08d938f5fe73167f7b