<h1 id="read-me!"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1e5c5afd-bf18-4a30-b370-ebfec7a0df1a/width=525/1e5c5afd-bf18-4a30-b370-ebfec7a0df1a.jpeg" />👇👀 Read me! 👇👀</h1>This is a bipolar slider for IllustriousXL. The purpose of this slider is to increase or decrease the subject's breast size in a controllable fashion with the LoRA input values. Higher positive LoRA input values result in larger breasts. Negative values results in smaller breasts.What makes this slider special is that it is largely decoupled from age. Making a breast size slider is not hard, making a breast size slider that doesn't overly influence age is hard. This slider does the best that modern tools allow for decoupling age from breast size, and in my opinion it does a good job at that.Version 1.0: Supported input values are <code>-5</code> to <code>5</code>, however weights of <code>4</code> or above often yield excessively large breasts. Version 2.0: Support input values are <code>-2</code> to <code>2</code> .Please be aware that whatever breast size you prompt (if any) will be the base that the slider works off of. For example, if you prompt <code>huge breasts</code> and then use a LoRA weight of <code>3</code>, you're going to get absolutely massive honkers. For the same prompt, if you prompt <code>flat chest</code> instead and use a LoRA weight of <code>3</code>, the breasts will be much smaller than if you used <code>huge breasts</code>. The LoRA slider works like an offset in this regard.No activation prompt. Example prompt (the showcase images use this style; booru tags work best):<code>&lt;lora:StS_IllustXL_Breast_Size_Slider_v2.0:1&gt;, masterpiece, best quality, 1girl, solo, adult woman, mature female, freckles, long red hair, knitted beanie, long camel wool coat, plaid scarf, leather gloves, jeans, ankle boots, cowboy shot, looking at viewer, smiling, holding paper shopping bag, snowy city street at dusk, christmas lights, falling snow, warm shop windows, bokeh</code>If you have issues using this LoRA, feel free to send me a message on CivitAI and I will help you out if I can. If you are running into use cases where this LoRA breaks down and/or freaks out, please let me know so I can fix it for future version releases.You can support my work by following me on CivitAI or <a target="_blank" rel="ugc" href="https://tensor.art/models/1061770966582985813">checking out TensorArt</a><a target="_blank" rel="ugc" href="https://tensor.art/models/1061770966582985813"> </a>where I also host my models.Changelog:January 20, 2025 - Initial v1.0 ReleaseOctober 31, 2026 - Version 2.0 Release (Happy Halloween!)

Files with SHA256: 7c3914e822e454e1873104b1d39e5adfd1bc3b3bafbf0d17f36a5b16aa14cc89