👇👀 Read me! 👇👀

This is a bipolar slider for ANIMA. The purpose of this slider is to make the subject's body heavier or slimmer in a controllable fashion with the LoRA input values. Higher positive LoRA input values result in a plumper, heavier body. Negative values result in a slimmer, skinnier body. It works on both women and men.

What makes this slider special is that it changes body weight and very little else. A weight slider that also ages your character, changes their outfit, swaps the background or reframes the shot is easy to make; one that doesn't is hard. This slider was trained against all of those: guards for apparent age (older and younger, for both women and men), muscularity, height, breast size and view angle, a style guard, and scenery-only preservation so backgrounds stay put. Outfits, faces, poses and framing stay put while the body changes.

Supported input values are -2 to 2. Around ±1 is the cleanest everyday range; ±2 is a strong very-skinny ↔ very-plump change. Women stay clean across the whole range. On men the extremes show a little drift: at the high end round cheeks can read slightly younger, and at the very thin end the head can look relatively large. Please be aware that whatever body type you prompt (if any) will be the base that the slider works off of. For example, if you prompt plump and then use a LoRA weight of 2, you're going to get a very heavy character. For the same prompt, if you prompt skinny instead and use a LoRA weight of 2, they will be much slimmer than if you used plump. 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 with Anima):

<lora:StS_Body_Weight_Slider_v1.0_ANIMA:1>, masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, score 9, safe, 1girl, solo, mature female, brown hair, long hair, wavy hair, swept bangs, brown eyes, looking at viewer, light smile, closed mouth, white shirt, t-shirt, denim jacket, open jacket, long sleeves, jeans, blue pants, sneakers, black footwear, standing, straight-on, arms behind back, full body, outdoors, city, street, sidewalk, storefront, building, day, sunlight

Showcase settings: hosekiLustrousmixAnima v1.0, Euler, Normal, 22 steps, CFG 3, Shift 1, 768x1024 or 1024x1024, Hires 2x with 4x_fatal_Anime_500000_G, 22 hires steps, denoise 0.3. Full parameters are embedded in every example image. For the cleanest slider sweeps, use a non-ancestral sampler (Euler rather than Euler a) and keep the seed fixed.

If you have issues using this LoRA, feel free to send me a message 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.

Changelog:

November 9, 2026 - Initial v1.0 Release