模型简介
模型特点
模型能力
使用案例
🚀 装饰性圣诞老人扩散模型
装饰性圣诞老人扩散模型是一个经过微调的Stable Diffusion模型，它基于 F222 进行训练，使用了超过两百张圣诞老人主题的装饰品和小摆设图片。该模型旨在捕捉圣诞老人给我们童年带来的那种奇妙感觉，每个人心中的圣诞老人形象各不相同，而这个模型希望能将这种独特的想象呈现出来。
🚀 快速开始
模型使用
- 在提示词中使用 orna santa 来激活模型。该模型在各种不同的装饰品上进行了训练，建议尝试不同生动的提示词变体。
示例输出
使用合并模型
增加更多深度：使用已编译的合并模型
- 下载位于 https://huggingface.co/3ee/ornamental-santa/tree/main 的
ornasanta_AnythingV3.0_fp16_0.3.ckpt文件。 - 将
ornasanta_AnythingV3.0_fp16_0.3.ckpt添加到你的Stable Diffusion模型中。 - 使用以下提示词表激活合并模型。
| 模型 | 提示词 |
|---|---|
| ornasanta | orna santa |
| AnythingV3 | 1girl, white hair, golden eyes, beautiful eyes, detail, flower meadow, cumulonimbus clouds, lighting, detailed sky, garden |
| Mo Di | modern disney style |
此模型与 Anythingv3 作为次要模型和 Mo Di Diffusion 作为第三模型进行了合并。
自行合并这些模型的设置
你也可以自行合并这些模型，见下表：
| 模型 | 权重 | 提示词 | 类型 |
|---|---|---|---|
| ornasanta | 0.3 | orna santa | 主要模型 |
| AnythingV3 | 0.3 | 1man | 次要模型 |
| Mo Di | 0.3 | modern disney style | 第三模型 |
合并模型示例输出
- 增强动漫风格的Anything模型：
- 在MoDi和Anything模型之间取得平衡：
- 更偏向MoDi模型：
- 额外示例：
- 更高细节：
💻 使用示例
提示词示例
基本起始点
orna santa with cookies
负向提示词
步数: 18, 采样器: Euler a, CFG比例: 11.5, 种子: 2480441584, 尺寸: 512x512, 模型哈希: b7ba5b22
圣诞老人装饰品插画
Perfectly-centered of orna santa mighty warrior standing in flower meadow, ((beautiful eyes)), highly detailed beard, ((dark fantasy)), dynamic lighting, stars, high quality, 4k, cover photo
负向提示词
步数: 60, 采样器: DDIM, CFG比例: 15, 种子: 3617510030, 尺寸: 512x512, 模型哈希: b7ba5b22
欢乐圣诞老人
orna santa, detailed face,trending on artstation, dark fantasy, illustrated by Alex Horley, Sophie Anderson
负向提示词
步数: 75, 采样器: Heun, CFG比例: 9, 种子: 1852604274, 尺寸: 512x512, 模型哈希: b7ba5b22
幻想圣诞老人装饰品
Perfectly-centered portrait-photograph of a real life godly orna santa with cookies descending from heaven, lifelike, super highly detailed, professional digital painting, artstation, concept art, Unreal Engine 5, Photorealism, HD quality, 8k resolution, cinema 4d, 3D, beautiful, cinematic, art by artgerm and greg rutkowski and alphonse mucha and loish and WLOP
负向提示词
步数: 80, 采样器: Heun, CFG比例: 8.5, 种子: 2837640579, 尺寸: 512x512, 模型哈希: b7ba5b22
圣诞老人面部装饰品
orna santa standing in a park
负向提示词
步数: 17, 采样器: Euler a, CFG比例: 7, 种子: 577494771, 尺寸: 512x512, 模型哈希: b7ba5b22
圣诞老人面部插画
Perfectly-centered portrait-photograph of a real life godly orna santa with cookies descending from heaven, lifelike, super highly detailed, professional digital painting, artstation, concept art, Unreal Engine 5, Photorealism, HD quality, 8k resolution, cinema 4d, 3D, beautiful, cinematic, art by artgerm and greg rutkowski and alphonse mucha and loish and WLOP
负向提示词
步数: 74, 采样器: DDIM, CFG比例: 4, 种子: 3376117548, 尺寸: 512x512, 模型哈希: b7ba5b22
合并模型提示词
这些提示词使用了位于 https://huggingface.co/3ee/ornamental-santa/tree/main 的合并模型 ornasanta_AnythingV3.0_fp16_0.3.ckpt。
激活F222和Mo - Di模型
Perfectly-centered portrait-photograph of a real life godly 1man orna santa with cookies descending from heaven, stars, lifelike, super highly detailed, professional digital painting, artstation, christmas decor, Unreal Engine 5, Photorealism, HD quality, 8k resolution, cinema 4d, 3D, beautiful, cinematic, modern disney style, white hair, golden eyes, beautiful eyes, detail, flower meadow, cumulonimbus clouds, lighting, detailed sky, garden,art by artgerm and greg rutkowski and alphonse mucha and loish and WLOP_
步数: 32, 采样器: DPM adaptive, CFG比例: 12, 种子: 1639653330, 尺寸: 512x512, 模型哈希: 697c8786
负向提示词
丹泽尔圣诞老人
Perfectly-centered portrait-photograph of a real life godly (((orna santa))) (((Denzel Washington))) 1man standing in flower meadow, beautiful eyes, highly detailed beard, ((sharp focus)), photo by Annie Leibovitz, intricate, natural lighting, stars, high quality, 4k, cover photo, modern disney style
负向提示词
步数: 91, 采样器: DPM++ 2S a Karras, CFG比例: 12, 种子: 2072333809, 尺寸: 512x512, 模型哈希: 254a9dce
迈克·泰森圣诞老人动漫风格
Perfectly-centered portrait-photograph of a real life godly ((orna santa)) (((Mike Tyson))) 1boy standing in flower meadow, beautiful eyes,((sharp focus)), photo by Annie Leibovitz, intricate, natural lighting, stars, high quality, 4k, cover photo, (((modern disney style)))
负向提示词
步数: 74, 采样器: DDIM, CFG比例: 4.5, 种子: 3117230049, 尺寸: 512x512, 模型哈希: 254a9dce, 去噪强度: 0.7
儿童泰森圣诞老人动漫风格 (使用相同提示词) 步数: 26, 采样器: DDIM, CFG比例: 7, 种子: 2757414259, 尺寸: 512x512, 模型哈希: 254a9dce, 去噪强度: 0.7
史蒂夫·卡瑞尔圣诞老人
orna santa steve carell standing in a park, ((sharp focus)), photo by Annie Leibovitz, intricate, natural lighting, high quality, 4k, cover photo
负向提示词
步数: 76, 采样器: DDIM, CFG比例: 11, 种子: 120176245, 尺寸: 512x512, 模型哈希: b7ba5b22
华金·菲尼克斯装饰品
(((orna santa))) (joaquin phoenix) hanging on Christmas tree, modern disney style
负向提示词
步数: 83, 采样器: LMS, CFG比例: 7.5, 种子: 297089387, 尺寸: 512x512, 模型哈希: b7ba5b22
华金·菲尼克斯动漫风格 (使用相同提示词) 步数: 83, 采样器: DPM++ 2S a, CFG比例: 10.5, 种子: 162322936, 尺寸: 512x512, 模型哈希: 254a9dce
摩根·弗里曼圣诞老人
Perfectly-centered portrait-photograph of a real life godly (((orna santa))) (((morgan freeman))) 1man standing in flower meadow, beautiful eyes, highly detailed beard, ((sharp focus)), photo by Annie Leibovitz, intricate, natural lighting, stars, high quality, 4k, cover photo, modern disney style
负向提示词
步数: 74, 采样器: DDIM, CFG比例: 4, 种子: 3376117548, 尺寸: 512x512, 模型哈希: b7ba5b22
罗宾·威廉姆斯圣诞老人
Perfectly-centered portrait-photograph of a real life godly (((orna santa))) (((robin williams))) 1man standing in flower meadow, beautiful eyes, highly detailed beard, ((sharp focus)), photo by Annie Leibovitz, intricate, natural lighting, stars, high quality, 4k, cover photo, modern disney style
负向提示词
步数: 91, 采样器: DPM++ 2M, CFG比例: 7.5, 种子: 3556207146, 尺寸: 512x512, 模型哈希: 697c8786
负向提示词模板
所有图像均使用以下负向提示词进行渲染：
((((ugly)))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))). out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck)))
Diffusers使用示例
此模型可以像其他Stable Diffusion模型一样使用。更多信息，请查看 Stable Diffusion。
导出模型：
from diffusers import StableDiffusionPipeline
import torch
model_id = "3ee/ornamental-santa"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "orna santa holding a plate of cookies"
image = pipe(prompt).images[0]
image.save("./santa_cookies.png")
📄 许可证
此模型为开放访问，所有人均可使用，采用CreativeML OpenRAIL - M许可证进一步规定了权利和使用方式。CreativeML OpenRAIL许可证规定：
- 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。
- 作者对生成的输出不主张任何权利，用户可以自由使用这些输出，但需对其使用负责，且使用不得违反许可证中的规定。
- 可以重新分发模型权重，并将模型用于商业用途和/或作为服务。如果这样做，请确保包含与许可证中相同的使用限制，并向所有用户分享CreativeML OpenRAIL - M许可证的副本（请完整仔细阅读许可证）。 请在此阅读完整许可证
Transformers 支持多种语言 Transformers 英语%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)