SlightlySimian Style Lora (Illustrious / Pony)

请先阅读“关于此版本”部分中的版本详情和建议。

LoRA，基于艺术家 SlightlySimian（又称 Simian）在 Civitai 上训练

通过以下链接支持该艺术家：

https://www.patreon.com/slightlysimian

https://x.com/slightlysinian

1. 始终使用标签 by slightlysimian

2. 此 LoRA 基于 Pony V6 版本 / Illustrious

3. 尽管使用了 Pony V6 基础模型，但在某些其他模型中使用时，图像可能会出现不一致，尤其是在 眼睛和手部，若在 Civitai 上使用，请使用一些 Embedding / Face Fix 以获得更好效果。对于使用 ComfyUI 的用户，最佳效果需搭配 Hirefix / DDetailer 来改善角色面部图像。

4. 不要忘记使用与 Pony 模型相关的标签

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,

5. 在 Civitai 上调整 LoRA 权重由您自行决定

6. 如果您希望生成彩色图像，请将 monochrome, greyscale, sketch 标签添加到 负面提示 中，因为该 LoRA 是由黑白图像或单一色系图像训练而成

7. 请先检查与您所选图像兼容的模型，某些模型会影响 LoRA 在最终图像生成中的效果，例如：兽人、人类、写实图像等。因此，同一模型并不总是适用于不同类型图像。

8. 如果您想强制图像生成器使用您选择的 LoRA 权重，请在正向提示中添加以下标签：

Illustrious (v1.0)

<lora:SlightlySimian_Style_Lora_Illustrious:1>

Pony (v1.0)

<lora:SlightlySimian_Style_Lora:1>

注意：LoRA 名称末尾的数字（1）表示 LoRA 权重。在图像生成器中，我们有滑块调节权重，但若您想“强制”使用，请在正向提示中使用与生成器滑块相同的数值，例如：

Illustrious (v1.0)

Civitai 滑块 = 1

正向提示: <lora:SlightlySimian_Style_Lora_Illustrious:1>

Pony (v1.0)

Civitai 滑块 = 1

正向提示: <lora:SlightlySimian_Style_Lora:1>

9. 我添加了与艺术家最知名角色相关的标签，若您希望生成接近某角色的图像，请记得输入角色名称，以下为每个角色的正向提示示例：

Molly

by slightlysimian, molly, cattle, bovid, bovine, horns, brown body, brown eyes, brown fur, brown hair , eyebrows, eyelashes, eyewear, hair, half-closed eyes, huge breasts, big breasts, narrowed eyes, eyebrow through hair, eyebrows, monotone hair, multicolored body, multicolored fur, pink areola, pink nipples, pink nose, pivoted ears, spots, spotted body, spotted fur, thick thighs, two tone body, two tone fur, wide hips

Mary

by slightlysimian, mary, sheep, bovid, caprine, domestic sheep, brown body, brown eyes, brown fur, brown horn, curved horn, head tuft, horn, inner ear fluff, mane, mane hair, multicolored body, multicolored fur, narrowed eyes, pivoted ears, tuft, two tone body, two tone fur, yellow body, yellow fur, yellow tail

Dawn

by slightlysimian, dawn, shark, marine, fish, brown eyes, big areola, big breasts, big nipples, breasts, curvy figure, huge breasts, tail, tail fin, tan body, thick thighs, voluptuous, voluptuous anthro, voluptuous female, white hair, wide hipped anthro, wide hipped female, wide hips

Hazel

by slightlysimian, hazel, deer, green eyes, breasts, brown areola, brown body, brown fur, chest tuft, mature anthro, mature female, multicolored body, multicolored ears, multicolored fur, small breasts, thick thighs, tuft, wide hipped female, wide hips, tan body, tan fur

Rose

by slightlysimian, rose, equid, equine, horse, brown body, brown eyes, brown fur, brown hair, long hair, multicolored body, multicolored fur, two tone body, two tone fur, white body, white fur, wide hipped female, wide hips, athletic, athletic anthro, athletic female, big breasts, hair, tail

以下为初始配置，但其他任何配置均可由您自行决定：

ILLUSTRIOUS

模型

Nova Furry XL - Illustrious 5.0

LoRA

SlightlySimian Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 （建议使用 1）

高级设置

CFG Scale - 3.0 ~ 9.0 （建议使用 6）

采样器 - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC （建议使用 Euler a）

步数 - 20 ~ 60 （建议使用 30）

Clip Skip - 1/2

VAE - SDXL VAE

正向提示

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by slightlysimian, furry, furry female, anthro, chicken, galliform, gallus (genus), phasianid, milf, mature female, 1girl, solo, blue eyes, white fur, white body, overweight female, slightly chubby, claws, toe claws, talons, tail feathers, feathers, avian feet, huge breasts, beak, full body, navel, looking at viewer, crossed arms, smile, feathers, featureless breasts, featureless crotch, wide hips, thick thighs

负向提示

bad quality, worst quality, worst detail, bad quality, worst quality, worst detail, sketch, censor, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, ai-generated, worst quality, low quality, off-topic, old, early, chromatic aberration, abstract, jpeg artifacts, scan artifacts, logo

---

PONY

模型

Pony Diffusion V6 XL - V6（请从这个开始）

LoRA

SlightlySimian Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 （建议使用 1）

高级设置

CFG Scale - 3.0 ~ 9.0 （建议使用 5）

采样器 - DDIM / Euler a / Euler / Heun / DPM2 / DPM++ 2M Karras / Uni PC （建议使用 Euler a）

步数 - 20 ~ 60 （建议使用 30）

Clip Skip - 1/2

VAE - SDXL VAE

正向提示

score_9, score_8_up, score_7_up, score_6_up, by slightlysimian, panda, bear, giant panda, 1girl, breasts, nipples, solo, green apron, apron, furry female, naked apron, furry, animal ears, green eyes, body fur, smile, collarbone, white hair, animal nose, looking at viewer, one breast out, huge breasts, thick thighs, white fur, cowboy shot, thighs, two-tone fur, standing, snout, wide hips, motion lines, bear ears, :3

负向提示

zPDXL3, 3D, 2D, human, monochrome, greyscale, sketch

由于该模型基于 Pony Diffusion，负向提示中无需过多设定，因为 Pony 模型本身非常灵活，但我始终保留 zPDXL-neg 标签（/model/332646/pony-pdxl-negative-embeddings）。

通用建议：

• 如有可能，请在使用此 LoRA 时注明作者 SlightlySimian 的署名。

• 请勿出售或商业使用此 LoRA。

• 请勿移除由 LoRA 生成图像的元数据。