<h3 id="raehoshi-illust-xl">Raehoshi Illust XL</h3>an enhanced iteration built upon the Illustrious XL model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.<hr />Why Early Access?Early access helps keep the project going. I don’t have my own GPU, so all training is done through rented cloud GPUs and that gets pretty expensive. By getting early access, you’re directly supporting the development of my models and helping me keep improving them. If you'd like to support me further, you can also <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">buy me a coffee on Ko-fi!</a> Every bit of help means a lot and keeps the future updates coming.<hr /><h3 id="recommended-setting">Recommended setting</h3>Positive prompt :<pre><code>masterpiece, best quality, very aesthetic, absurdres</code></pre>Negative prompt :<pre><code>bad quality, worst quality, jpeg artifacts, sketch, bad anatomy, signature, watermark</code></pre>Steps : 25+CFG : 5-7Sampler : euler a or dpm++2m karras (euler for vpred)Standard resolution :<pre><code>832 x 1216, 1216 x 832, 1152 x 896, 896 x 1152, 1344 x 768, 768 x 1344, 1024 x 1024</code></pre>High resolution :<pre><code>1024 x 1536, 896 x 1536, 1536 x 1024, 1536 x 896</code></pre>Hires.fix Setting:<ul><li>Upscaler : <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-Remacri">4x Foolhardy Remacri</a></li><li>Hires step : 10-15</li><li>Denoise : 0.1-0.3</li></ul><h3 id="special-tags">Special Tags</h3>Quality Tags:<ul><li>masterpiece</li><li>best quality</li><li>good quality</li><li>average quality</li><li>bad quality</li><li>worst quality</li></ul>Rating Tags:<ul><li>safe</li><li>sensitive</li><li>nsfw</li><li>nsfw, explicit</li></ul>Aesthetic Tags:<ul><li>very aesthetic</li><li>aesthetic</li><li>displeasing</li><li>very displeasing</li></ul><h3 id="training-details">Training Details</h3>The model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.Stage 1<ul><li>Dataset : v1-31k, v2-37k, v3-34k, v4-60k, v5_v5.1-18k, v6-15k, v7-39k, v8-41k, v9-30k, v10-30k with multi resolution</li><li>Hardware : 2x A100 80gb, v3, v4, v5, v5.1-2x H100 80gb, v7,v8, v9, v10-RTX PRO 6000</li><li>Batch size : 32</li><li>Gradient accumulation steps : 2</li><li>Learning rate : 6e-6</li><li>Text encoder : 3e-6</li><li>Epoch : 15</li></ul>Stage 2<ul><li>Dataset : v1-2.5k, v2 and v3-2.3k, v4-2.5k, v5-2k, v5.1-1.8k, v6-1.5k, v7-1.7k, v7.1,v8-4.1k, v9-1.9k, v10-2.4k</li><li>Hardware : 1x A100 80gb, v7_v7.1,v8, v9, v10-RTX PRO 6000</li><li>Batch size : 48</li><li>Gradient accumulation steps : 1</li><li>Learning rate : 3e-6, v5.1-2.5e-6</li><li>Text encoder : disable</li><li>Epoch : 15</li></ul><h3 id="list-of-new-seriescharacters-trained:">List of New Series/Characters Trained:</h3><ul><li>Zenless Zone Zero</li><li>Wuthering Waves</li><li>Honkai: Star Rail</li><li>Genshin Impact</li><li>Arknights: Endfield</li><li>Umamusume</li><li>Azur Lane</li><li>Arknights</li><li>Fate/GO</li><li>Dandadan</li><li>Make heroine ga oo sugiru</li><li>Kusuriya no Hotorigoto</li><li>Hololive from justice and dev is</li><li>Indie Vtuber Dooby, Yuuki Sakuna, Nimi Nightmare, and S***</li><li>100 girlfriends who really love you</li><li>Haite kudasai takamine-san</li><li>Alina clover</li><li>Nikke: bready and little mermaid</li><li>Kpop Demon Hunters</li></ul>Full character list are available <a target="_blank" rel="ugc" href="https://civarchive.com/articles/23522">article here</a>For character trait details prompts, please refer to the Danbooru site for accurate tags and references.<h3 id="license">License</h3><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a><h1></h1>Special thanks to Joe for supporting my worksSpecial thanks to Juno for supporting my works and help me with early tester

Raehoshi illust XL

<ul><li>Based on Illustrious 1.1</li><li>Support up to 1536x resolution</li><li>Added new knowledge character series:<ul><li>Zenless Zone Zero</li><li>Wuthering Waves</li><li>Honkai: Star Rail</li><li>Genshin Impact</li><li>Hololive member</li><li>Dandadan</li><li>Makeine</li></ul></li></ul>

raehoshiIllustXL_v40.safetensors

v4.0

v10.0

vpred v2.0

v9.1

v9.0

v8.1 aesthetic

vpred_v1.0

v8.0

v7.1

v7.0

v6.0

v5.1

v5.0

v3.0

v2.1

v2.0

v1.0-spo_edition

v1.0

Raehoshi Illust XLan enhanced iteration built upon the Illustrious XL model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.Why Early Access?Early access helps cover the cost of training and development. By purchasing early access, you're directly supporting the development of my models. If you'd like to support me further, you can also <a target="_blank" rel="ugc" href="https://ko-fi.com/raelina">buy me a coffee on Ko-fi!</a> Your support keeps the project going and ensures even better models in the future.Recommended settingPositive prompt :masterpiece, best quality, good qualityNegative prompt :lowres, bad quality, worst quality, bad anatomy, sketch, jpeg artifacts, signature, watermarkSteps : 25-28CFG : 5-6Sampler : euler_aSupported resolution :1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536Hires.fix Setting:<ul><li>Upscaler : <a target="_blank" rel="ugc" href="https://nmkd.de/?esrgan">4x NMKD YandereNeo XL</a></li><li>Hires step : 10-15</li><li>Denoise : 0.1-0.3</li></ul>Training DetailsThe model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.Stage 1<ul><li>Dataset : v1-31k, v2-37k, v3-34k, v4-60k</li><li>Hardware : 2x A100 80gb, v3 and v4-2x H100 80gb</li><li>Batch size : 32</li><li>Gradient accumulation steps : 2</li><li>Learning rate : 6e-6</li><li>Text encoder : 3e-6</li><li>Epoch : 15</li></ul>Stage 2<ul><li>Dataset : v1-2.5k, v2 and v3-2.3k, v4-2.5k</li><li>Hardware : 1x A100 80gb</li><li>Batch size : 48</li><li>Gradient accumulation steps : 1</li><li>Learning rate : 3e-6</li><li>Text encoder : disable</li><li>Epoch : 15</li></ul>List of New Series/Characters Trained:<ul><li>Zenless zone zero series character</li><li>Wuthering waves series character</li><li>Hololive from justice and dev is</li><li>HSR character from 2.2 - 3.2 version</li><li>Genshin character from 5.0 - 5.4 version</li><li>Tokidoki bosotto roshia-go de dereru tonari no alya-san series</li><li>Dandadan</li><li>Make heroine ga oo sugiru</li></ul>For character prompts, please refer to the Danbooru site for accurate tags and references.License<a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>Special thanks to Joe for supporting my works

Files with SHA256: 1e8288345e3a0a5d3ca35733573e71eea00abac015dce0b86d30a9811b17aeba