Asian Role
模型简介
混合模型,结合国风3与Chilloutmix特性,擅长生成亚洲风格角色图像,支持动漫与写实风格
模型特点
亚洲美学风格
专为亚洲角色设计,融合中国古典美学与现代动漫风格
双模型融合
结合国风3与Chilloutmix模型优势,实现风格多样性
精细控制
通过负面提示词系统可精细控制生成质量
多平台兼容
支持Diffusers库和stable-diffusion-webui两种主流框架
模型能力
动漫风格图像生成
写实风格人像生成
场景生成
角色细节控制
负面提示过滤
使用案例
角色设计
动漫角色生成
通过简短提示词生成高质量动漫角色
示例展示银发蓝眸少女形象
写实人像生成
生成具有东方特征的写实风格人像
示例包含少女与少年肖像
场景设计
幻想场景构建
生成包含复杂光影的花园、宫殿等场景
示例展示花海与浮空宫殿场景
🚀 asian-role
欢迎来到 asian-role 模型,这是一个具有中国华丽古风风格的游戏角色模型。该模型旨在仅通过少量提示词,就能生成高质量、高细节的动漫风格图像。
例如,输入 1girl, white hair, beautiful blue eyes, red lips, detailed sky, garden 就能生成相应的图像。
这个模型是一个融合模型,它融合了 GuoFeng3 和 Chilloutmix。
🚀 快速开始
在线体验
我们支持通过 Gradio Web UI 来运行该模型: https://huggingface.co/spaces/shibing624/asian-role
使用 Diffusers 库
这个模型可以像其他 Stable Diffusion 模型一样使用。更多信息,请查看 Stable Diffusion。
你还可以将模型导出为 ONNX、MPS 和/或 FLAX/JAX 格式。
from diffusers import StableDiffusionPipeline
import torch
model_id = "shibing624/asian-role"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.safety_checker = lambda images, **kwargs: (images, False)
prompt = "1girl"
negative_prompt = """(((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly, pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation, deformed, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs, bad feet, loli, little girl"""
image = pipe(prompt, height=512, width=512, num_inference_steps=30, guidance_scale=6,
negative_prompt=negative_prompt, num_images_per_prompt=1).images[0]
image.save("./1girl.png")
在 NovelAI/stable-diffusion-webui 中使用
这个模型可以在 AUTOMATIC1111/stable-diffusion-webui 中使用。
只需将模型文件 asian-role.safetensors 放到 stable-diffusion-webui/models/Stable-diffusion 目录下即可,无需额外的 VAE 模型,该模型已包含 VAE。
💻 使用示例
基础用法
以下是使用该模型生成图像的示例:
动漫女孩:
{{{masterpiece}}}, {{best quality, super fine illustration , beautiful and delicate water,The finest grass}}. ((beautiful eyes)),{ very delicate light, perfect and delicate limbs}, {nature, painting, water spray},{{ fine luminescence ,very fine 8K CG wallpaper}},Lavender eyes, pink pupils, whole body, white hair, bright eyes,( (an extremely delicate and beautiful girl)), ((1 girl)), medium bust, dynamic angle, (white dress with gold decoration), (long hair flowing with the wind, beautiful hair ornaments, delicate wet skirt, nsfw, breeze, long bangs between eyes), wrinkled skirt, (staring blankly, lovely big eyes),messy_hair,payot,Lateral braid,(Tulle lace white skirt),flowers and grass meadow, near the water edge, ((sunset, starry sky in a circle), randomly distributed clouds, (((river))), splashing water, falling petals
Negative prompt: (((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly, pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs, bad feet, loli, little girl
Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 1, Size: 618x768, Model: asian-role
真实女孩:
(Masterpiece),(best quality),((masterpiece)),(highres), original, portrait of a beautiful teenager, small breasts, formal dress, soft smile, red lips, nice hair, beauty eyes, 1girl, solo, realism, {{{{drawn by Xi Zhang}}}}
Negative prompt: (((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly, pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs, bad feet, loli, little girl
Steps: 23, Sampler: Euler, CFG scale: 7, Seed: 1, Size: 618x768, Model: asian-role
真实男孩:
(Masterpiece),(best quality),((masterpiece)),(highres), original, portrait of a beautiful young man, handsome, smile, short hair, beauty eyes, 1boy, solo, realism, formal dress, chinese face, {{{{drawn by Ralph Steadman}}}}
Negative prompt: (((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly, pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs, bad feet, loli, little girl
Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 1, Size: 618x768, Model hash: 60dbd0f982, Model: asian-role
场景:
(extremely detailed CG unity 8k wallpaper),(((masterpiece))), (((best quality))), ((ultra-detailed)), (best illustration),(best shadow), ((an extremely delicate and beautiful)),dynamic angle,floating, fairyland,dynamic angle,sea of flowers,beautiful detailed garden,wind,classic,spring, (detailed light),feather, nature, (sunlight), river, forest,(((floating palace))),((the best building)),beautiful and delicate water,(painting),(sketch),(bloom),(shine)
Negative prompt: (((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly, pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs, bad feet, loli, little girl
Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 1, Size: 618x768, Model: asian-role
高级用法
使用建议
推荐设置:
- 提示词:
{best quality}, {{masterpiece}}, {highres}, {an extremely delicate and beautiful}, original, extremely detailed wallpaper, 1girl
- 负提示词:
(((simple background))),monochrome ,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, ugly,pregnant,vore,duplicate,morbid,mut ilated,tran nsexual, hermaphrodite,long neck,mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,bad anatomy,bad proportions,malformed limbs,extra limbs,cloned face,disfigured,gross proportions, (((missing arms))),(((missing legs))), (((extra arms))),(((extra legs))),pubic hair, plump,bad legs,error legs,username,blurry,bad feet
- 采样步数:30 或 50
- 采样器:DPM++ SDE Karras
- 图片尺寸:至少为 768
- 推荐提示词关键词:
strapless dress, smile, chinese dress, dress, hair ornament, necklace, jewelry, long hair, earrings, chinese clothes
📄 许可证
该模型是开放访问的,所有人都可以使用,并遵循 cc-by-sa-4.0 许可证,该许可证进一步规定了使用权利和使用方式。
cc-by-sa-4.0 许可证规定:
- 你不得使用该模型故意生成或分享非法或有害的输出或内容。
- 作者对您生成的输出不主张任何权利,您可以自由使用它们,但需对其使用负责,且使用不得违反许可证中的规定。
- 您可以重新分发模型权重,并将该模型用于商业用途或作为服务使用。如果您这样做,请务必包含与许可证中相同的使用限制,并向所有用户提供一份 CreativeML OpenRAIL - M 许可证副本(请完整、仔细阅读许可证)。 请在此阅读完整许可证
Stable Diffusion V1 5
Openrail
稳定扩散是一种潜在的文本到图像扩散模型,能够根据任何文本输入生成逼真的图像。
图像生成
S
stable-diffusion-v1-5
3.7M
518
Stable Diffusion Inpainting
Openrail
基于稳定扩散的文本到图像生成模型,具备图像修复能力
图像生成
S
stable-diffusion-v1-5
3.3M
56
Stable Diffusion Xl Base 1.0
SDXL 1.0是基于扩散的文本生成图像模型,采用专家集成的潜在扩散流程,支持高分辨率图像生成
图像生成
S
stabilityai
2.4M
6,545
Stable Diffusion V1 4
Openrail
稳定扩散是一种潜在文本到图像扩散模型,能够根据任意文本输入生成逼真图像。
图像生成
S
CompVis
1.7M
6,778
Stable Diffusion Xl Refiner 1.0
SD-XL 1.0优化器模型是Stability AI开发的图像生成模型,专为提升SDXL基础模型生成的图像质量而设计,特别擅长最终去噪步骤处理。
图像生成
S
stabilityai
1.1M
1,882
Stable Diffusion 2 1
基于扩散的文本生成图像模型,支持通过文本提示生成和修改图像
图像生成
S
stabilityai
948.75k
3,966
Stable Diffusion Xl 1.0 Inpainting 0.1
基于Stable Diffusion XL的潜在文本到图像扩散模型,具备通过遮罩进行图像修复的功能
图像生成
S
diffusers
673.14k
334
Stable Diffusion 2 Base
基于扩散的文生图模型,可根据文本提示生成高质量图像
图像生成
S
stabilityai
613.60k
349
Playground V2.5 1024px Aesthetic
其他
开源文生图模型,能生成1024x1024分辨率及多种纵横比的美学图像,在美学质量上处于开源领域领先地位。
图像生成
P
playgroundai
554.94k
723
Sd Turbo
SD-Turbo是一款高速文本生成图像模型,仅需单次网络推理即可根据文本提示生成逼真图像。该模型作为研究原型发布,旨在探索小型蒸馏文本生成图像模型。
图像生成
S
stabilityai
502.82k
380
精选推荐AI模型
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型,性能媲美GPT-3.5-turbo,优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型
Transformers 支持多种语言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型,专为边缘设备推理设计,体积仅为Cosmo-3B模型的2%左右。
对话系统
Transformers 英语

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型,适用于从给定文本中提取答案的任务。
问答系统 中文
R
uer
2,694
98