<h1 id="introduction-to-beholder-vision-4zn376cka">Introduction to Beholder Vision</h1>Beholder Vision began as an experimental LyCORIS-LoCon for <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765?modelVersionId=889818">Illustrious-XL v0.1</a>, trained on 126 meticulously curated images of aesthetic anime art.The concept: create “eye-candy” results, with flexibility to adapt to a variety of creative needs.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/11a02868-a4ea-4ffe-a7b3-063484a9e80c/width=525/11a02868-a4ea-4ffe-a7b3-063484a9e80c.jpeg" /><h2 id="usage-recommendations-x3a5v9ec8">Usage Recommendations</h2>Illustrious Ver. Parameters (Recommended as of Nov 30, 2024):<ul><li>Strength: 1.0–1.2 (personally go for just 1.0)</li><li>Sampler: DPM++ 2M SDE (Karras)</li><li>Steps: 25–35</li><li>CFG Scale: 6–7</li></ul><h2 id="changelog-and-updates-pwxime30j">Changelog and Updates</h2>Dec 6, 2024 Version 3o is here!<ul><li>Full support for v-prediction models such as <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1093948">NoobAI-XL V-Pred-0.65S-Version</a>, which this version is based on.</li></ul>Dec 4, 2024 Version <a target="_blank" rel="ugc" href="https://civarchive.com/models/998729?modelVersionId=1129863">2.1o</a> is now available! This marks a complete rework of the initial test version for Pony. It has been trained for 5,490 steps, making it competitive with the original Beholder Vision.<ul><li>Despite its extensive improvements, the new LoRA is just 54.8MB—half the size of previous Pony iterations of the model and vastly enhanced in every aspect.</li></ul>Dec 2, 2024The first version of Beholder Vision for FLUX.1 [dev], <a target="_blank" rel="ugc" href="https://civarchive.com/models/998729?modelVersionId=1122834">1.3o</a>, is now out.Nov 30, 2024 I’m excited to announce Beholder Vision 1o (and its successor, 1.1o)!<ul><li>1o debuts as an experimental GLoRA, while 1.1o returns to classic LoCon, delivering improved performance at a smaller file size.</li><li>Now natively compatible with other SDXL models, including <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1022833">NoobAI-XL Epsilon-pred 1.0-Version</a>.</li></ul>This version represents a significant leap forward over the 0.9beta, thanks to an upgraded training dataset and finely tuned parameters. (Details on the dataset and parameters will be shared if there’s interest.)

【LyCORIS / Illustrious-XL & NAI-XL】L3n4's Beholder Vision

beholder_vision-3o.safetensors

3o NAI-XL v-pred

2o-PXL

1.1o IL

1o IL

0.9b IL

Introduction to Beholder VisionBeholder Vision began as an experimental LyCORIS-LoCon for <a href="https://civitai.com/models/795765?modelVersionId=889818" rel="ugc noopener noreferrer nofollow" target="_blank">Illustrious-XL v0.1</a>, trained on 126 meticulously curated images of aesthetic anime art.The concept: create “eye-candy” results, with flexibility to adapt to a variety of creative needs.Usage RecommendationsIllustrious XL Ver. Parameters (Recommended as of Nov 30, 2024):<ul><li>Strength: 1.0–1.2 (personally go for just 1.0)</li><li>Sampler: DPM++ 2M SDE (Karras)</li><li>Steps: 25–35</li><li>CFG Scale: 6–7</li></ul>Changelog and UpdatesDec 6, 2024Version 3o is here!<ul><li>Full support for v-prediction models such as <a href="https://civitai.com/models/833294?modelVersionId=1093948" rel="ugc noopener noreferrer nofollow" target="_blank">NoobAI-XL V-Pred-0.65S-Version</a>, which this version is based on.</li></ul>Dec 4, 2024Version <a href="https://civitai.com/models/998729?modelVersionId=1129863" rel="ugc noopener noreferrer nofollow" target="_blank">2.1o</a> is now available! This marks a complete rework of the initial test version for Pony. It has been trained 5,490 steps, making it competitive with the original Beholder Vision.<ul><li>Despite its extensive improvements, the new LoRA is just 54.8MB—half the size of previous Pony iterations of the model and vastly enhanced in every aspect.</li></ul>Dec 2, 2024The first version of Beholder Vision for FLUX.1 [dev], <a href="https://civitai.com/models/998729?modelVersionId=1122834" rel="ugc noopener noreferrer nofollow" target="_blank">1.3o</a>, is now out.Nov 30, 2024I’m excited to announce Beholder Vision 1o (and its successor, 1.1o)!<ul><li>1o debuts as an experimental GLoRA, while 1.1o returns to classic LoCon, delivering improved performance at a smaller file size.</li><li>Now natively compatible with other SDXL models, including <a href="https://civitai.com/models/833294?modelVersionId=1022833" rel="ugc noopener noreferrer nofollow" target="_blank">NoobAI-XL Epsilon-pred 1.0-Version</a>.</li></ul>This version represents a significant leap forward over the 0.9beta, thanks to an upgraded training dataset and finely tuned parameters. (Details on the dataset and parameters will be shared if there’s interest.)

Files with SHA256: a76d091b1948cee5e55b16f72f9759616f3a2135b7ce113d6386f127ad34c94c