Furlana Style Lora (Illustrious / Pony)

详情

模型描述

请先阅读“关于此版本”部分中的版本详情和建议。

LoRA,基于毛茸茸艺术家 Furlana 在 Civitai 上训练

也被称为 czekolana / furlana_art / furlana6039 / furlanart / sketchlana / sketchphobia

请通过以下链接支持该艺术家:

https://www.patreon.com/furlana

https://www.furaffinity.net/user/furlana

https://www.deviantart.com/furlana

https://inkbunny.net/furlana

https://furlana.sofurry.com

https://www.weasyl.com/~Furlana

https://furlanart.tumblr.com

https://sketchphobia.tumblr.com

https://bsky.app/profile/furlana.bsky.social

https://www.youtube.com/@furlana6039

https://www.instagram.com/czekolana

https://www.facebook.com/furlanart

https://picarto.tv/furlana

https://subscribestar.adult/furlana

https://ko-fi.com/furlana

https://gumroad.com/furlana

https://trello.com/b/b7Q04nty/furlanas-queue-updates

https://toyhou.se/furlana

https://x.com/furlana_art

  1. 始终使用标签 by furlana

  2. 此 LoRA 基于 Pony V6 版本 / Illustrious

  3. 尽管使用了 Pony V6 基础模型,但在 Civitai 上使用其他模型时,图像中某些部分(尤其是 眼睛和手部)可能出现不一致。建议使用一些 Embedding / Face Fix 以获得更好的效果。对于使用 ComfyUI 的用户,最佳效果可通过使用 Hirefix / DDetailer 来改善角色面部细节获得。

  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,
  1. 在 Civitai 上调整 LoRA 权重由您自行决定。

  2. 为了在 Civitai 上更佳地使用 LoRA,我建议使用 VAE (SDXL VAE) 以及 Embedding (Pony PDXL Negative Embeddings),以减少手部和眼睛细节的错误。

  3. 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 是基于黑白图像或单一配色方案训练的。

  4. 如果您希望强制图像生成器使用您选择的 LoRA 权重,请在正向提示中使用以下标签:

Illustrious (v1.0)

<lora:Furlana_Style_Lora_Illustrious:1>

Pony (v1.0)

<lora:Furlana_Style_Lora:0.8>

注意:LoRA 名称末尾的数字(如 0.8)表示 LoRA 权重。在图像生成器中我们通常使用滑块调节权重,但如果您想“强制”使用特定权重,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:Furlana_Style_Lora_Illustrious:1>

Pony (v1.0)

Civitai 滑块 = 0.8

正向提示: <lora:Furlana_Style_Lora:0.8>
  1. 我添加了与艺术家最知名角色相关的标签。如果您希望生成接近该角色的图像,请记得输入角色名称。以下为每个角色的正向提示示例

Lana Baginsky

by furlana, lana baginsky, red panda, ailurid, furry, anthro, brown body, brown fur, white hair, brown areola, brown nipples, green eyes, mature female, big breasts, natural breasts, raised eyebrow, markings, medium hair, fur, eyebrows, yellow sclera, tail, orange body, orange fur, white fur, white body, multicolored body, multicolored fur, wide hips, thick thighs, 1girl, solo, breasts, sweater, half-closed eyes, furry female, furry, tail, animal ears, smile, off shoulder, large breasts, collarbone, cowboy shot, naked sweater, body fur, looking at viewer, long sleeves, happy, bottomless, bare shoulders, standing, grabbing own breast, orange background, gradient background

以下为初始配置,但您可自由调整任何其他配置:

ILLUSTRIOUS (v1.0)

模型

WAI-NSFW-illustrious-SDXL - v14

LoRA

Furlana 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 7)

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 furlana, furry, furry female, anthro, lana baginsky, red panda, ailurid, furry, anthro, brown body, brown fur, white hair, brown areola, brown nipples, green eyes, mature female, big breasts, natural breasts, raised eyebrow, markings, medium hair, fur, eyebrows, yellow sclera, long tail, orange body, orange fur, white fur, white body, multicolored body, multicolored fur, wide hips, thick thighs, 1girl, solo, animal ears, blue background, yellow background, simple background, gradient background, arms behind head, brown hair, cowboy shot, looking at viewer, smile, cleavage, latex, black bodysuit, glistening clothing, arms up, belt, mole, bodysuit, center opening, standing, no bra, plunging neckline, grin, unzipped, teeth, wide hips, zipper, open clothes, parted lips, contrapposto, collarbone, half-closed eyes, black belt, long sleeves

负向提示

monochrome, greyscale, sketch, bad quality, worst quality, worst detail, sketch, censor

PONY (v1.0)

模型

DucHaiten-Pony-XL (no-score) - v6.0

LoRA

Furlana Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (建议使用 0.8)

高级设置

CFG Scale - 3.0 ~ 9.0 (建议使用 7)

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, by furlana, domestic dog, canine, canid, canis, 1girl, breasts, nipples, solo, jewelry, nude, brown hair, furry female, furry, food, animal ears, bracelet, fruit, tail, water, cup, partially submerged, lips, earrings, brown eyes, necklace, drinking glass, medium breasts, borrowed character, pool, ass, holding, curly hair, looking at viewer, ice cream

负向提示

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

由于此模型基于 Pony Diffusion,负向提示中无需过多指定,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,在使用此 LoRA 时请注明作者 Furlana 的署名。

  • 请勿出售或商业化此 LoRA。

  • 请勿移除由该 LoRA 生成图像的元数据。

此模型生成的图像

未找到图像。