QGO PromptingReal
8317°
<qgo-real>
支持 ModelTrends 标签的应用允许你通过在提示中复制这段代码来运行/安装模型，无需任何设置。请在支持该功能的应用中寻找我们的图标，比如下面的 Prism。
运行此模型
优惠 / 广告
Easy Creator (Prism) 网页
不限量 · 固定费用
最适合初学者。强大的工作流程，学习曲线低。
PirateDiffusion Telegram
不限量 · 固定费用
创建视频、图像、自定义聊天角色等。
Pro studio (SpyGlass) 网页
不限量 · 固定费用
从任何浏览器或手机浏览模型、渲染和优化。
Discord bot (Vector)
不限量 · 固定费用
将 Vector 添加到你的服务器或加入 Vector Discord。创造任何东西！
Unified Editor 网页
不限量 · 固定费用
图像和视频编辑器：在同一页面渲染、编辑、放大等。
Civitai 网页
按次付费
在Civitai官网生成；每张图片用Buzz积分支付。
本地应用
需设置
如果你的电脑硬件够好，可以安装本地程序。
ModelDuel 网页
按次付费
一次在多达50个检查点/基础模型上生成相同的提示。
QGO Prompting Real V1 by QEGo is a full model checkpoint merge, a base art style for your realistic image creations. The creator's civitai notes state that it was designed for minimal prompting, but as this is a checkpoint merge and the example image prompts are very long, I would take it with a grain of salt... use strong negatives and a booster like fc-portrait for better results Example prompt /render /parser:new /sampler:dpm2m /size:768x832 /seed:1862676218 /guidance:6 (candid frontal closeup close up body portrait of a ((Russian woman:1.2)) model (with long Blonde Pixie Cut Haircut:1.2),…QGO Prompting Real V1 by QEGo is a full model checkpoint merge, a base art style for your realistic image creations. The creator's civitai notes state that it was designed for minimal prompting, but as this is a checkpoint merge and the example image prompts are very long, I would take it with a grain of salt... use strong negatives and a booster like fc-portrait for better results Example prompt /render /parser:new /sampler:dpm2m /size:768x832 /seed:1862676218 /guidance:6 (candid frontal closeup close up body portrait of a ((Russian woman:1.2)) model (with long Blonde Pixie Cut Haircut:1.2), (posing in Dazzling Ballroom with Shimmering Dance Floor and Twinkling Lights during Snow Level:1.1), (wearing Glamorous Hollywood Film Star Fashion with Satin Gowns and Fur Stoles:1.2), at dark night, moonlight, (naughty), (Saluting:1.1), Dappled light Hair light, (bright flash photography:1.2), Deep reds aesthetic, (focus on the eyes), (hard shadows, pitch black brackground, unlit, dark theme, dim lighting, deep contrast:1.1), (background in focus), (wearing Futuristic Post-Apocalyptic Survivor Attire with Tattered Leather Jackets and Goggles:1.2), analog film grain overexposed blurry polaroid) [[[ comic, illustration, painting, airbrushed, glossy, render, animation, 3d shaders, monochrome, sepia, deformed, text]]]
创作者说明
Hello world
Let's get real
It's been a while since the last update, and this iteration is quite different than the last. That's not to say it is necessarily groundbreaking compared to anything else on this website (it's a merge after all), but I've tried to focus on a couple of very specific things:
-
A high amount of realism without any use of LoRAs or embeddings.
Having a good basis provides a lot of room to go crazy with those later.
-
Functional with a limited/small negative prompt.
Similarly, a small negative prompt often makes for the most realistic outputs. It is always possible to write your novel, or add embeddings in there along the way.
-
Consistency in poses / hands / other features within these constraints.
-
Decent control over light and darkness through prompt alone
There are great LoRAs out there for lighting / noise offset, but there is already some great functionality by default.
-
Responsiveness to the wildest lists of wildcards ChatGPT has to offer.
I like to have random lists of locations, time periods, clothing/materials, concepts, all generated (and embellished) by your local GPT.
Recommended VAE (not included):
-High base resolutions are advised: such as 640x896 for a portrait format
-If possible use hires.fix or a similar implementation: a denoise of 0.3~0.5 will do well in most situations various give good results. is the one used in all examples here, but there are other great options.
-Don't feel obligated to use time consuming samplers such as the one in most examples. I was suffering from a short bout of SDE Karras addiction when generating the examples, but I have since come back to 2M Karras @ 15~20 steps, which is usually my baseline and more than fine on its own (even with hires.fix).
*Note that some of the example prompts can generate nudity, prompt against this to prevent it. For actual examples of nudity you can check out the album uploaded separately.
**The model in the metadata is QGO-3002a, which is the same as QGO-PromptingReal-v1
SHA256
1EABE50675224173CBDB2C96C745E55790BCA4620C06B406D6935DB0516FDA19
QGO PromptingReal 热度趋势
热度分数，过去12个月
热度评分
8,317°
本周
▼
0.5%
8,319° 当时，8,317° 现在
本月
▼
2.3%
8,328° 当时，8,317° 现在
过去一年
▼
27.2%
8,459° 当时，8,317° 现在
7,000°
起点
评分范围是 0° 到 9,999°。低于 7,000° 的部分保留给还没有任何来源报告的模型，这些模型用替代数值填充，保证列表完整。7,000° 是有实际数据的起点：一个有真实数据但几乎没人下载的模型就在这里，后续的度数都是基于它的测量。起点本身不反映模型质量，只有起点以上的度数才区分不同模型。
+1,280°
Civitai 下载量
该版本在Civitai上有16,279次下载。下载是最重要的因素，按对数刻度计数：下载量增加十倍，热度增加300°，所以百万下载的模型不会比千次下载的热度高一千倍。六个下载来源共享该指标，按各自下载量比例分配。
+466°
点赞数
各来源累计点赞数为 1,280。点赞权重是下载量的一半，按同样的对数比例计算。
+30°
采用率
每天大约 2 次下载，基于两次来源读取间的测量，不是用历史平均估算。下载速度权重是下载项的四分之一，这样能反映新热度，但不会让一天的峰值超过多年累计。
+150°
完整模型
+150°，因为这是完整模型：一个检查点，权重本身。LoRA 或嵌入是附加在别人权重上的，不会超过同等流行度的检查点。
−609°
年龄
−609°，因为 SD15 权重发布于 2022。每个模型继承其权重的年龄：每年扣 150°，最多扣 750°，直到达到上限。没有这个扣减，排行榜前列会被 2022 和 2023 年的检查点占据，因为它们下载量积累了多年。
显示详细分解
本站上的每个数字都可以查证。这个模型的热度评分是 8,317°，这里一步步展示了它是如何组成的，每一步都有累计总分：起点、每个来源增加的度数、模型类型的加成以及权重年龄的扣减。颜色对应上方图表的区间。最后的词汇表解释了所有术语。
- 1从起点开始。为什么是 7,000° 而不是零：评分范围是 0° 到 9,999°，低于 7,000° 的部分保留给还没有任何来源报告的模型，这些模型用替代数值填充，保证列表完整且不会超过有数据的模型。7,000° 是有实际数据的起点。一个有真实数据但几乎没人下载的模型就在这里；后续的度数都是测量值，起点以上有十个十倍下载阶梯，每阶梯增加 300°。起点对所有模型一样，不影响排名；区分模型的是起点以上的度数。7,000°累计总数
- 2加上下载量。总共16,279个下载等价量，来自Civitai 下载量。下载量增加十倍，热度增加相同的300°，所以大小很重要，但不会让分数失控。+1,280°8,280°累计总数
- 3加上点赞数。1,280个点赞和竖起大拇指，权重是下载量的一半。+466°8,746°累计总数
- 4增加采用率。现在大约每天2次下载，基于两次读数的差值，权重是四分之一。+30°8,776°累计总数
- 5完整模型的额外加分。检查点包含权重本身；附加组件不会超过同等受欢迎度的完整模型。+150°8,926°累计总数
- 6去除年龄。SD15权重发布于2022：每年扣除150°，最多扣除750°，直到达到最大值。−609°8,317°累计总数
- =热度得分。这个模型在本站所有榜单上的排名。没有其他因素会调整它。8,317°
术语表：这里用到的术语
- 热度得分
- 一个数字，表示模型当前的使用和需求程度，范围从0°到9,999°。本站所有标注为最热门的榜单都按这个分数排序，别无他物。
- 基准线
- 所有有真实数据的模型起始于7,000°。分数范围是0°到9,999°；基准线以下的部分保留给无数据的替代模型，这样有数据的模型总是排在无数据模型之上。基准线对所有人相同，不影响排名；超过基准线的度数才是实际测量值。
- 下载等价量
- 得分中当作下载计算的所有项目总和：下载本身，每个种子上传者算1,000，每个AI Horde图片和每次生成网站的运行算一个。
- 对数刻度
- 以十为单位计数，而不是以一为单位：从1,000到10,000下载增加的热度和从10,000到100,000增加的热度相同。这样可以防止巨头压倒一切。
- 点赞
- 来自所有来源的点赞和竖起大拇指，每个点赞在对数刻度上价值半个下载。
- 采用率
- 模型当前每天的下载次数，基于两次读数的差值。权重是下载项的四分之一。
- 测量与估算
- 测量表示有两个来源的读数，且差异是真实的。估算表示只知道今天的总数，过去的数据是根据模型的生命周期分配的；网站会说明显示的是哪种。
- 做种者
- 指那些在线保存权重副本供他人通过种子下载的人，或者提供同样服务的托管镜像。每个做种者相当于1000次下载。
- AI Horde
- 一个志愿者网络，在捐赠的电脑上免费生成图片。它用某个模型生成的图片数量是公开的，每张图片算作一次下载。
- 生成网站
- 托管自己模型副本并允许用户生成的站点，比如PixAI、SeaArt和Yodayo。它们的下载计数和Civitai一样，每次生成算一次下载。
- OpenRouter 令牌
- 通过API提供的文本模型，如Claude或GPT，没有权重需要下载，因此其使用量以令牌计量：过去30天内通过OpenRouter（一种许多应用使用的网关）读取和生成的文本片段。每10,000,000个令牌计为一次下载。来源：OpenRouter (openrouter.ai/rankings)，CC BY 4.0。
- 完整模型（检查点）
- 权重文件本身，是能独立生成的文件。它会获得额外加分，因为附加组件依赖它。
- LoRA和嵌入
- 小型附加文件，用来引导别人的权重朝向某种风格、角色或概念。它们不能单独运行。
- 家族与权重
- 模型构建所基于的基础，比如SD 1.5、SDXL、Flux或Wan。每个模型继承其家族权重的发布日期。
- 年龄
- 根据家族权重发布多久，扣除的度数：每年150°，最多750°。它保留了那些积累了多年下载量的老模型，防止它们被挤出榜单顶部。
- 家族加成
- 对当前网站重点推广的某个家族的LoRA给予的小幅度限制性加分，总是在分数细目中列出。
- 替代分数
- 给还没有任何来源报告的模型一个稳定的最低分数，这样榜单才完整。它永远不会高于有数据的模型。
- 新模型！（宽限期）
- 不到7天的新模型显示“新模型！”而非分数，且不参与排名。其分数从第一天开始计算，但一天大的模型增长最快，若不等待，周榜#1总是昨天刚发布的模型，而非持续一周的。
- 趋势
- 模型在某段时间内的增长与同一时间段内典型模型增长的对比。比典型快表示上升，比典型慢表示下降。
- 典型模型
- 目录的中间值：一半有数据的模型增长比它快，一半比它慢。
这个模型的受欢迎程度相对于整个目录的变化：它在每个时间段内下载量、点赞和使用量的增长，和同一时间段内典型模型的增长相比，以及当时的热度分数。高于典型增长表示上升，低于则表示下降。过去的数据是从今天的总数、模型的第一天和测量的下载速度（如果有两次测量）推算出来的；如果模型在某个时间段开始时不存在，则显示为 n/a。
示例作品
以下提示词和参数由在 Civitai 上创作这些作品的人分享。选择一张作品查看它是如何生成的。
参数
采样器
DPM++ 2M
步数
30
引导强度
5
种子
4162761812
尺寸
648x912
提示词
highlight the peaceful mood, (abstract:.63), (feminine:.46)
负面提示词
((nudity)), JuggernautNegative-neg
参数
采样器
DPM++ SDE Karras
步数
20
引导强度
5
种子
1862676218
尺寸
640x896
提示词
candid frontal closeup close up body portrait of a (Russian woman:1.2) model (with long Blonde Pixie Cut Haircut:1.2), (posing in Dazzling Ballroom with Shimmering Dance Floor and Twinkling Lights during Snow Level:1.1), (wearing Glamorous Hollywood Film Star Fashion with Satin Gowns and Fur Stoles:1.2), at dark night, moonlight, (naughty), (Saluting:1.1), Dappled light Hair light, (bright flash photography:1.2), Deep reds aesthetic, (focus on the eyes), (hard shadows, pitch black brackground, unlit, dark theme, dim lighting, deep contrast:1.1), (background in focus), (wearing Futuristic Post-Apocalyptic Survivor Attire with Tattered Leather Jackets and Goggles:1.2), analog film grain overexposed blurry polaroid
负面提示词
(comic, illustration, painting, airbrushed, glossy, render, animation, 3d:1.1) shaders, monochrome, sepia, deformed
参数
采样器
DPM++ SDE Karras
步数
20
引导强度
6
种子
2700113389
尺寸
640x896
提示词
high angle portrait of a glamorous hollywood (black African American man:1.3), (working as a janitor inside a deserted museum:1.2), at night, (mopping the reflective wet floor), luminous (bright camera flash photography:1.2), Earth tones aesthetic, (focus on the eyes), (hard shadows, pitch black background, unlit, dark theme, dim lighting, deep contrast:1.1), (background in focus), (motion blur, lens blur, out of focus:1.1)
负面提示词
(comic, illustration, painting, airbrushed, glossy, render, animation, 3d:1.3) shaders, deformed, sepia, monochrome
参数
采样器
DPM++ SDE Karras
步数
20
引导强度
3
种子
2348915488
尺寸
640x896
提示词
(realistic, award winning color photograph) dark closeup close up nude body portrait of a young (black African girl:1.2) model (with long Pastel pink Asymmetrical Cut Haircut:1.2), (working in Stunning Serengeti National Park in Tanzania with Safari Wildlife and Wide Open Plains:1.1), (wearing Gothic Lolita Style with Ruffled Dresses and Lace Parasols:1.2), at noon, crowded surrounded by men, reluctantly exposing her naked little tits, (smug), (Hands on her head:1.1), , (Glowing Low-key lighting photography:1.1), high contrast aesthetic, (focus on the eyes), angelic, beautiful face,(hard shadows, pitch black brackground, unlit, dark theme, dim lighting, deep contrast:1.2), (background in focus)
负面提示词
(comic, illustration, painting, airbrushed, glossy, render, animation, 3d:1.1) shaders, monochrome, sepia, deformed, child
参数
采样器
DPM++ 2M SDE Karras
步数
30
引导强度
7
种子
172684410
尺寸
408x640
提示词
1936, empty pub, london, beautiful woman, 29 years old, big breasts, (light silk dress:1.4), arm tattoos, tattoos all over body, many tattoos, british, dirty hair, wavy hair, messy hair, short hair bangs, wavy bangs, dark blonde hair, light silk dress, serving a beer, very hot, sweaty body, dirty hair, Hyper realistic, Scorsese, film grain, cinematic lighting, telelens, atmospheric, movie still, high quality, normal hands, detailed fingers,masterpiece,
负面提示词
glasses, top hat, white hair, EasyNegative, fat, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), bad anatomy, text, error, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad feet, poorly drawn face, bad proportions, gross proportions, ng_deepnegative_v1_75t, badhandsv5-neg
参数
采样器
DPM++ SDE Karras
步数
20
引导强度
5
种子
2290194292
尺寸
640x896
提示词
(candid voyeuristic portrait from outside through a drive-through window at a fast food restaurant:1.12) closeup dark (dirty window reflection glare:1.1) of a nude Glamorous Hollywood (Spanish woman:1.2) model (with long Sandy blonde Slicked-Back Cut Haircut:1.2), (working in the shade behind a window checkout counter:1.1), (wearing a red and yellow store uniform with cropped shirt with a company logo on it:1.2), at night, exposed naked very small chest and hairy pussy (vagina labia), (annoyed look), (embarrassed covering), Luminous Ring light, fisheye telephoto lens dust, (bright camera flash photography:1.3), Rustic earth tones aesthetic, (focus on the eyes), Concealer, (hard shadows, pitch black background, unlit, dark theme, dim lighting, deep contrast:1.35), (background in focus), (motion blur, lens blur, out of focus:1.2)
负面提示词
(comic, illustration, painting, airbrushed, glossy, render, animation, 3d:1.3) shaders, deformed
参数
采样器
Euler a
步数
10
引导强度
1.7
种子
1753378051
尺寸
639x936
Clip skip
2
提示词
9((Hyper-Surrealistic ancient aatomic artifact))BREAK((((modern living room [mahogany | oak | maple | cherry |teak] furniture)))BREAK(((psychadelic trippy carpeting)))((Creative((Photo Masterpiece 8k wallpaper [Verb | adjective | pronoun])))BREAK(dodge and burn, corner edge darken vignette)((exposure POP!!!) hdr extremely intricate, High (Detail:1.1), Sharp focus, dramatic cinematic light, 8k textures, elegant, ((((cinematic look))))breathtaking, insane details)) <lora:Details-Slider:0.5> <lora:ExposureControl:0.7> <lora:LCM_1-5:0.6> <lora:up-down_lighting:2> <lora:ColorTempSliders:3><lora:DepthOfFieldSliders:0.5> <lora:epiC35mm:0.3> <lora:HDhelper:0.6> <lora:back-front_lighting:-2> <lora:ContrastControl:1.8> <lora:CuteHorrorSlider:0.9> <lora:Saturation:1.1>
负面提示词
(((nsfw))), (((cleavage:1.3))), ((neckline)), ((nudity)), (cleft), (((neckline))), plastic, canvas frame, cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), blurry, (((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))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, 3d render, (tiara), (badhands5)
参数
采样器
DPM++ SDE Karras
步数
20
引导强度
3
种子
1611226943
尺寸
640x896
提示词
low angle portrait of a pale ginger woman holding a red cat in her arms, (she is wearing a green knitted sweater:1.2), they are curled up in a comfortable chair (in front of a window, It is snowing outside:1.2), blissful, (warm christmas lights inside). warm deep reds, (camera flashlight photography:1.2), background in focus, (hard shadows, pitch black background, unlit, dark theme, dim lighting, deep contrast:1.25)
负面提示词
(comic, illustration, painting, airbrushed, glossy, render, animation, 3d:1.3) shaders, deformed, sepia, monochrome
本地运行
QGO PromptingReal 是 Stable Diffusion 1.5 系列的一个基础模型，收录于 ModelTrends.ai——一个只读的开源 AI 图像、视频和文本模型目录。你可以将它与其他 Stable Diffusion 1.5 模型比较，查看热度分数了解趋势，并在 PirateDiffusion 或 BitVector 上打开试用。
按模型系列浏览
Text / LLM 模型
434
Anima 模型
528
Chroma 模型
19
Fibo 模型
2
Flux 模型
1,496
Flux 2 / Klein 模型
1,239
Flux 3 模型
3
Moss 模型
3
Iris 模型
1
MiniMax H3 模型
364
Hunyuan 模型
204
Ideogram 模型
20
Krea2 模型
717
Qwen 模型
20
Qwen2 模型
47
Ltx2 模型
153