Lonbluewolf 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。

在 Civitai 上基于毛茸茸艺术家 Lonbluewolf 训练的 LoRA

请通过以下链接支持该艺术家:

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

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

  1. 始终使用标签 by lonbluewolf

  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,图像可能在 眼睛和手部 出现不一致。若在 Civitai 上使用,请添加一些 Embedding / Face Fix 以获得更好效果。对于使用 ComfyUI 的用户,建议配合 Hirefix / DDetailer 来改善角色面部细节。

  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. 为在 Civitai 上更好地使用 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. 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,尤其针对:毛茸茸、人类、写实图像等 类型。因此,同一模型未必适用于所有图像类型。

  4. 若要强制图像生成器使用您选择的 LoRA 权重,请在正向提示词中添加以下标签:

Illustrious (v1.0)

<lora:Lonbluewolf_Style_Lora_Illustrious:0.8>

Pony (v1.0)

<lora:Lonbluewolf_Style_Lora:0.8>

注意:LoRA 名称末尾的数字(0.8)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”使用特定权重,请在正向提示词中使用与生成器滑块相同的数值,例如:

Illustrious (v1.0)

Civitai 滑块 = 0.8

正向提示词: <lora:Lonbluewolf_Style_Lora_Illustrious:0.8>

Pony (v1.0)

Civitai 滑块 = 0.8

正向提示词: <lora:Lonbluewolf_Style_Lora:0.8>

注意:该艺术家使用了多个知名的毛茸茸角色(卡通、电影、漫画等),但在训练中我保持了 LoRA 的灵活性和可混合性,以便与其他 LoRA 组合使用。我的建议是,您应使用特定角色的 LoRA,以确保最终结果令人满意。

以下为初始配置,但您也可自由选择其他配置:

ILLUSTRIOUS

模型

Nova Furry XL - Illustrious v4.0

LoRA

Lonbluewolf Style Lora - v1.0 (illustrious) - 0.5 ~ 1.0 (推荐 0.8)

高级设置

CFG Scale - 3.0 ~ 9.0 (推荐 6)

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

步数 - 20 ~ 60 (推荐 50)

Clip Skip - 1/2

VAE - SDXL VAE

正向提示词

masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, scenery, depth of field, scenery, volumetric lighting, by lonbluewolf, furry, furry female, anthro, tauren, warcraft, bovid, bovine, 1girl, solo, puffy anus, nipples, brown hair, brown tail, brown horns, pussy, tail, big butt, butt focus, nude, animal ears, large breasts, bedroom eyes, looking back, blue eyes, tattoo, half-closed eyes, bent over, looking at viewer, from behind, smile, long hair, snout, presenting, clitoris, presenting anus, presenting hindquarters, presenting pussy, tavern background, beer, glistening body, shiny body

负向提示词

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

WAI-ANI-NSFW-PONYXL - v6.0

LoRA

Lonbluewolf Style Lora - v1.0 (Pony) - 0.5 ~ 1.0 (推荐 0.8)

高级设置

CFG Scale - 3.0 ~ 9.0 (推荐 7)

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

步数 - 20 ~ 60 (推荐 30)

Clip Skip - 1/2

VAE - SDXL VAE

正向提示词

score_9, score_8_up, score_7_up, by lonbluewolf, skunk, mephitid, black fur, 1girl, breasts, solo, tail, ass, skunk tail, blue eyes, nipples, anus, pussy, animal ears, presenting, presenting hindquarters, presenting butt, green socks, bottomless, furry female, against wall, alley, graffiti, furry, bag, looking back, from behind, half-closed eyes, socks, shirt lift, shoulder bag, skunk ears, clothes lift, grey hair, large breasts, big butt, wide hips, curvy figure, voluptuous, makeup

负向提示词

zPDXL3, 3D, 2D, human

由于此模型基于 Pony Diffusion,负向提示词中无需过多设定,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:

  • 使用此 LoRA 时,如有可能,请注明作者 Lonbluewolf 的署名。

  • 不得出售或商业化此 LoRA。

  • 不得移除由该 LoRA 生成图像的元数据。

此模型生成的图像

未找到图像。