<h1 id="raemora-xl-2j8rtq937">Raemora XL</h1>Pony-based SDXL model that focuses on high-quality anime with a more versatile style.<h3 id="-5wdyit0s1"></h3><hr />Enjoying my work? Consider supporting the development of my models by buying me a coffee on <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">Ko-fi</a>Also check out my other models on Mage: <a target="_blank" rel="ugc" href="https://www.mage.space/play/55ee9a305fc7e3572509def13acbefbf">Raepix Focus XL</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/08df2e9b11b4d9587dcbb6846a9dda11">Raepix Focus XL Lightning</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/41658a734e3918e89e700c76f103ffc7">Raevitamix Realistic</a> / <a target="_blank" rel="ugc" href="https://www.mage.space/play/b1586a8de40e97411fdcda1fe03ceb60">Raevista XL</a><hr /><h3 id="recommended-settings-e1axhh7cr">Recommended settings</h3>To guide the model towards generating high-aesthetic images, use quality prompts like:<pre><code>score_9, score_8_up, score_7_up, source_anime,</code></pre>For more higher quality outcomes, prepend negative prompts with:<pre><code>score_4_up, score_5_up, score_6_up, lowres, messy drawing, amateur drawing, ugly face, bad face, bad teeth, (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands, bad anatomy), watermark,</code></pre><h3 id="multi-aspect-resolution-w7vx6ce9z">Multi Aspect Resolution</h3>This model supports generating images at the following dimensions:| Dimensions | Aspect Ratio ||--------------|---------------|| <code>1024 x 1024</code> | 1:1 Square || <code>1152 x 896</code> | 9:7 || <code>896 x 1152</code> | 7:9 || <code>1216 x 832</code> | 19:13 || <code>832 x 1216</code> | 13:19 || <code>1344 x 768</code> | 7:4 Horizontal || <code>768 x 1344</code> | 4:7 Vertical || <code>1536 x 640</code> | 12:5 Horizontal || <code>640 x 1536</code> | 5:12 Vertical |<h3 id="hires.fix-settings-vsbukrz7d">Hires.fix Settings</h3><ul><li>Upscaler : <a target="_blank" rel="ugc" href="https://nmkd.de/?esrgan">4x-NMKD_YandereNeoXL</a></li><li>Hires step : 10-15</li><li>Denoising : 0.1-0.3</li></ul>The model is finetuned with selected high-quality anime images. No additional character training was done, some characters may have been learned.

Raemora XL

Reduced 3D dataset and increased 2D dataset to decrease the likelihood of random 3D outputs in some prompts, so you don't need to put 3D in negative.

RaemoraXLv2.safetensors

v2.0

v3.0

v1.0

Raemora XLPony-based SDXL model that focuses on high-quality anime. This model is like a Raemu/Raena variant but with pony as its base.⬇Share your cool creation below⬇If you enjoy my work and like it, you can support me at <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">Ko-fi</a>Recommended settingsTo guide the model towards generating high-aesthetic images, use quality prompts like:score_9, score_8_up, score_7_up, intricate details,For more higher quality outcomes, prepend negative prompts with:score_4_up, score_5_up, score_6_up, lowres, messy drawing, amateur drawing, ugly face, bad face, bad teeth, (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands, bad anatomy), watermark,* Some prompts might appear with strong 3D or realistic elements. Using negative prompts like "3D" or "realistic" might help (fixed in v2).Multi Aspect ResolutionThis model supports generating images at the following dimensions:| Dimensions | Aspect Ratio ||--------------|---------------|| <code>1024 x 1024</code> | 1:1 Square || <code>1152 x 896</code> | 9:7 || <code>896 x 1152</code> | 7:9 || <code>1216 x 832</code> | 19:13 || <code>832 x 1216</code> | 13:19 || <code>1344 x 768</code> | 7:4 Horizontal || <code>768 x 1344</code> | 4:7 Vertical || <code>1536 x 640</code> | 12:5 Horizontal || <code>640 x 1536</code> | 5:12 Vertical |Hires.fix SettingsUpscaler : 4x-NMKD_YandereNeoXLHires step : 10-15Denoising : 0.1-0.3The model is finetuned with selected high-quality anime images. No additional character training was done, some characters may have been learned.Reduced 3D dataset and increased 2D dataset to decrease the likelihood of random 3D outputs in some prompts, so you don't need to put 3D in negative.

Files with SHA256: 0c78c81ffbd1603feb7b6e884ed5a217669baf2afbc8aacf478dbd81b9ba3009