Basic knowledge :
- Installation and problem solving reference: " Windows installation Stable Diffusion WebUI and problem solving records ";
- Problems when running and using " Sorting out various problems encountered when Windows uses Stable Diffusion ";
- Model application and parameters " Stable Diffusion Personally Recommended Various Models, Setting Parameters, Extended Applications, etc. Collection ";
- Prompt Words Create Spells " AI Drawing Prompt Words/Spells/Affixes/Keywords Usage Guide (Stable Diffusion Prompt Designer Operation Manual) ";
- Different types of models Models description " Analysis of different types of StableDiffusion model Models ";
- Draw character movements and details of hands and feet " Stable Diffusion Accurately draw character movements and details of hands and feet (ControlNet extension required) ";
- Comparison of various styles and practical application " AI drawing style comparison table / detailed research records and experience summary of drawing style samples ";
Advanced practice :
- AI drawing practice (1): making a shopping cart icon icon
- AI drawing practice (2): Make a picture book painting of the ocean, beach, boy and dog
- AI drawing actual combat (3): hand-drawn mech violent man
- AI drawing practice (4): related picture png and icon icon used in making food safety PPT
- AI drawing practice (5): Enlarge and restore old photos, mosaic photos, ID photos
- AI drawing practice (6): Make a poster to celebrate Labor Day
- AI drawing practice (7): interior design line draft rendering, landscape design hand draft modification, architectural photos to line draft
- AI drawing practice (8): three views of making game character manuscripts
- AI drawing practice (9): Make pictures for popular songs
- AI drawing practice (10): line draft vector diagram of a woman with a headscarf
- AI drawing practice (11): Modify paper children's drawings into electronic photos
1. Basic overview
If you have mastered the basics and want to directly find Chinese and English affixes, please turn to the prompt list in the fifth part of this article.
- The prompt word (
prompt) consists of multiple affixes. - Prompts are divided into positive prompts (
positive prompt) and reverse prompts (negative prompt), which are used to tell AI what is needed and what is not.
Reverse cues are descriptions of what we don't want to happen.
Example: NSFW content that is not suitable for watching at work, including restricted ratings, low-quality images, and descriptions of easily deformed body parts.
Note: You can download the file of Easynegative. It has integrated some commonly used reverse prompt words. We only need to input keywords to get better results.
Put it in/enbeddingsthe folder , and entereasynegativeactivation in the reverse prompt when it needs to be triggered.
- The default value of the weight of the affix is 1, which is weakened from left to right, and the weight will affect the screen generation result.
For example, if the scenery tag is in the front, the character will be small, and on the contrary, the character will become larger or half-length.
Choosing the correct order and grammar to use the prompt words will show the desired picture better, faster and more efficiently.
Note that because the affixes are in English, we need to study many words in depth.
For example, the word running, running is the default word, and the alias is run, but if the model used in this article uses run, it will be almost invalid. See the first example in the weight article to understand.
- AI will selectively execute according to probability. If there is a conflict between prompt words, AI will randomly choose which prompt word to execute according to the probability determined by the weight.
- The size of the generated image will affect the effect of the prompt. The larger the image, the more prompts are needed, otherwise the prompts will pollute each other.
- Prompt supports the use of emoji, and the expressiveness is better, and the effect can be achieved by adding emoji pictures. If you like the expression, you can repair your hands.
For ease of understanding, unrelated affixes can be distinguished by newlines.
- This article is mainly to learn the changes in the graphs brought about by the changes of affixes. Different models generate different graphs. When learning, you need to observe the changes in the graphs under the same model.
- The following are the main parameters for reference. Set a negative word when learning, and the rest can be defaulted.
// 参考
absurdres, 8k, comic, viewfinder, 1male, run, black hair, orange sun, blue sky,
Negative prompt: easynegative, canvas frame, cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((close up)),((b&w)), wierd colors, 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
Steps: 20, Sampler: Euler a, CFG scale: 22, Seed: -1, Face restoration: CodeFormer, Size: 720x480, Model hash: 1dceefec07, Model: dreamshaper_331BakedVae, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, Hires upscale: 2, Hires upscaler: Latent
2. Weight Grammar
weight logic
-
If you want to clarify a certain subject, you should make its generation steps forward, increase the number of generation steps, sort the affixes forward, and increase the weight.
画面质量→主要元素→细节 -
If you want to clarify the style, the style affix should be better than the content affix
画面质量→风格→元素→细节 -
Unconfirmed: The style weight may need to be higher than the picture quality, so that the special style texture will not be polluted by the picture quality.
separator
,Comma : divides the affixes, and has a certain weight sorting function. The weight before the comma is high, and the weight after the comma is low, so it is recommended to sort:
- Summary (image quality + painting style + lens effects + lighting effects + theme + composition)
- Subject (character & object + pose + clothing + props)
- Details (scene + environment + accessories + features)
Example 1:
// 超高分辨率， 8k， 漫画风， 相机取景框，一个男子， 奔跑（动词原型）， 黑色头发， 橙色太阳， 蓝色天空
absurdres, 8k, comic, viewfinder, 1male, run, black hair, orange sun, blue sky,
According to the picture shown above, all the elements have appeared, but runthis keyword has not been realized. Except for a few running characters in the lower left corner of the first picture, the third picture has no characters.
Example two:
// 超高分辨率， 8k， 漫画风， 相机取景框， 一个男子， 奔跑（现在分词）， 黑色头发， 橙色太阳， 蓝色天空
absurdres, 8k, comic, viewfinder, 1male, running, black hair, orange sun, blue sky,
And when we changed to run, runningthe running posture came out~~.
combinator
:Colon : custom weight value
format: left parenthesis + affix + colon + number + right parenthesis
// 单人女孩词缀，权重为0.75
(1girl:0.75)
()Parentheses only : Increase the weight by 0.1
and use parentheses in most cases.
// 权重乘以1.1
(1girl)
{}curly braces : add weight 0.05
// 权重乘以1.05
{
1girl}
[]Square brackets : reduce the weight by 0.1, and it is said that it is reduced by 0.05.
The weight value in the square brackets cannot be customized, and the customized weight can only use(x:0.5)the form.
// 权重除以1.1
[1girl]
(()),{ {}},[[]]multiplexing parentheses : overlay weight
// 权重乘以1.1*1.1，即权重为1.21
((1girl))
General process: first write down the picture to be described and generate it once, and then try to modify the unsatisfactory or missing description according to the generated result. The concept to be emphasized is increased by the grammatical form of (xxx: 1.x ), where xxx is your The word to be emphasized, 1.x represents the ratio to be improved, such
1.5as to increase the weight by 150%.
The weight range is 0.4-1.6. If the weight is too small, it is easy to be ignored, and if the weight is too large, it is easy to make mistakes in fitting the image. Example:(beautiful:1.3).
Overlay weight: increase the weight by stacking parentheses, each additional layer is equivalent to increasing the weight by 1.1 times, for example:((((beautiful eyes)))).
Example 3:
According to the rules of the previous example, increase the jump and strengthen its weight, so the image changes~~
// 跳跃的权重最高
(absurdres), 8k, comic, ((viewfinder)), 1male, running, (jumping:1.5), black hair, orange sun, blue sky,
It can be seen that the characters have a sense of running and jumping, but the sense of jumping is definitely the strongest.
Joiner
ANDAnd : Aggregate multiple affixes in a prompt word sequence position, and their initial weights are the same
// 三个词缀权重一致
bird and dog and pig
// 可使用冒号标记其权重
bird:1.5 and dog:1.2 and pig:0.8
In actual use, it is found that using and to connect affixes may cause objects to merge, such as cabbage and meat, which may generate a weird picture of meat wrapped in cabbage.
Example 4:
OK, let’s change the above case to see what effect it will have:
// 合并了绿色、白色、长发，要求加强绿色头发，橙色和蓝色天空合并，权重一致
absurdres, 8k, comic, [viewfinder], (1male), (running), (green hair:1.5 and white hair and very long hair), orange sun and blue sky,
As can be seen from the picture above, the protagonist’s hair must be green, but there may be 0~2 characters with white hair appearing in the screen, and the rule of 1male is broken; the orange sun and the blue sky have the same weight,
so Basically, they will appear in the picture at the same time (Looking at the cloud: it seems that AI wants to embed both orange and blue in it, and the third picture seems to want to pinch them together bluntly, and this feeling is in the previous examples. pictures are not available).
+plus
(red hair:1.1)+(yellow hair:1.25)+(green hair:1.4)
|vertical line
(red hair:1.1)|(yellow hair:1.25)|(green hair:1.4)
_underline
(red hair:1.1)_(yellow hair:1.25)_(green hair:1.4)
- add nothing
andAffixes will merge objects, but in the case of 什么都不加or ,commas, the possibility of this merge is very low.
(red hair:1.1)(yellow hair:1.25)(green hair:1.4)
,Comma
When the objects are consistent, the comma has the function of connecting
(red hair:1.1),(yellow hair:1.25),(green hair:1.4)
Example five:
Although they are all connectors, there are still some slight differences. Whether they tend to be more integrated or juxtaposed, you can explore by yourself~~
// 又跑又跳，红黄绿色头发，橙色太阳和蓝色天空~~
absurdres, 8k, comic, [viewfinder], (1male), running|jumping, (red hair:1.1)(yellow hair:1.25)(green hair:1.4), (orange sun)_(blue sky),
Well, this example completely confuses the picture~~haha, one of the reasons is: an element with too high a weight may pollute other elements.
3. Distribution and alternate rendering
[]:If symbols such as , and are used in square brackets |, more complex distribution and alternate rendering requirements can be achieved.
[A:B:step][Element 1:Element 2:Step Ratio] : Render element 2 after the progress of rendering element 1, and realize the mutual superposition of element 1 and element 2. It has a feeling similar to [from:to:when] and can be used for two fusion of terms
// 渲染蓝色到40%进度后，开始渲染红色
[blue:red:0.4]
// 前12步渲染蓝色后，开始渲染红色
[blue:red:12]
Note:
When step > 1, it means how many steps before the combination is rendered as A, and then as B.
When step < 1, it means the percentage of iteration steps (total number of steps involved).
[A:step][Element 1: Step Scale] : From what progress to start rendering element 1
// 在执行40%的步骤后，开始渲染蓝色
[blue:0.4]
// 在执行15步之后，开始渲染蓝色
[blue:15]
[A::step][Element 1::step ratio] : stop the rendering of element 1 when the progress of rendering is reached (the rendering of other elements continues)
// 在执行了40%的步骤后，停止渲染蓝色
[blue::0.4]
// 在执行了15步后停止渲染蓝色
[blue::15]
[A|B][Element 1|Element 2] : Alternate mixed rendering of element 1 and element 2, which means rendering A once, rendering B again, rendering A again~~ and so on until the end
// 融合蓝色与红色，紫色？
[blue|red]
// 某物与某物的交替演算，用于生成融合生物，句中词缀含义为融合牛与马。
[cow|horse]
[xx|xx|xx|xx|xx…] is essentially a fusion of affixes under equal weight to generate a single element, without limiting the number of mixed elements.
[A|B]C[Element 1|Element 2]Element 3 :
Brackets plus an affix imply a shared element in the fusion process.
Example seven:
// 一个蓝红混色染发的短发女孩
1girl, [blue|red]hair, short hair
Sure enough, purple came out~~
Example eight:
// 合成“空中的鸟”与“空中的飞机”
[bird|airplane] in sky
What a weird combination~~
Example nine:
After learning, now we use the affixes in the first example to make a few more pictures to practice.
// 哇哦哇哦哇哦
absurdres, 8k, comic, [viewfinder], 1male+running, 1female ([red:blue:0.3]hair)(long hair) jumping, [[orange sun]], [blue sky], (bird and horse) in sky,
Note:
Because of the addition of animals,femalandmalemay be recognized as female or male by AI. . .
At present, it is found that it is difficult to successfully generate pictures by only using words to describe multiple characters in the same scene. In the case, men and women are mixed, and there are many wrong pictures that I have not put up.
It may be necessary to add a lot of negative prompts to control pollution, and to clearly tell the AI the location and status of different characters, so that the chance of success is high.
It is recommended to use manuscripts, controlnet, etc. to achieve it together.
Example ten:
On the other hand, the realization of a single scene and a single person is particularly easy, which may be the reason why many AI picture websites make pictures of a single person.
best quality, very detailed, absurdres, 8k, comic, [viewfinder], one lady with long [blue|red]hair is sitting on ground, birds around her, blue sky+[orange sun],
The prompt words here use the human English reading format~~
4. Call the LoRA & Hypernetworks model
<>Angle brackets : invoke LoRA or hypernetwork models, etc.
Input:<lora:filename:multiplier>or<hypernet:filename:multiplier>to call the corresponding model.
<lora:cuteGirlMix4_v10:0.5>
Note: Make sure that the relevant model files have been saved in the […\models\lora] or […\models\hypernetworks] folder.
5. Resources
Affix acquisition channel
tag auto-completion plugin
-
Plug-in name :
tagcomplete
After the installation is complete, follow the tutorial to update the translation library: https://www.bilibili.com/video/BV14Y4y1D7vR -
Key affixes :
Trigger Words
When using some lora models, you need to use the officially provided trigger words as affixes to accurately guide different styles in a single lora.
Since there are no preview images and notes, it is difficult to use affixes, and it is difficult to distinguish whether they are effective or not in complex environments.
It is recommended to installcivitai helperfor automatic generation of preview images withtrigger words.
Reverse prompt word plugin
- Easynegative ：https://github.com/MeccaStudio/EasyNegative
- badhandv4：https://huggingface.co/AsciiP/badhandv4/tree/main
easynegativeWhen using it, write: , in the reverse prompt word badhandv4, but be careful, it may cause some model styles to be wrong after use.
prompt word list
- Reverse commonly used :
((nsfw)),((ugly))),(((duplicate))),((morbid)),((mutilated)),(((tranny))),(((trans))),((trannsexual))),(((mutation))),(((deformed)))(((long neck))),((bad anatomy))(((bad proportions))),(((extra arms))),(((extra legs))), (((disfigured))),((more than 2 nipples))),malformed,mutated,(hermaphrodite),((extra limbs)).((missing arms)).((missing legs)).((poorly drawn hands))((poorty drawn face)),(mutation,poorly drawn :1.2),(long body :1.3).multiple breasts,cloned face,gross proportions, mutated hands,bad hands,bad feet,long neck,missing limb,(malformed limbs),malformed hands,(fused fingers).(too many fingers),extra fingers,missing fingers,extra digit,fewer digits,(mutated hands and fingers :1.5),low res,text,error,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,text font ui,futa,yaoi,- 画质常用：
masterpiece, best quality, masterpiece,best quality,official art,extremely detailed CG unity 8k wallpaper,- 地点常用：
masterpiece, best quality, masterpiece,best quality,official art,extremely detailed CG unity 8k wallpaper, steam, in the cyberpunk city, explosion, underwater, flower field, fireworks, intense shadows, strong rim light, golden hour lighting, sky, sea, mountain, on a hill, the top of the hill, in a meadow, plateau, on a desert, cityscape, in hawaii, landscape, beautiful detailed sky, beautiful detailed water, on the beach, on the ocean, beautiful purple sunset at beach, over the sea, in the ocean, against backlight at dusk,- 风格常用：
artbook, game_cg, comic, 4koma, animated_gif, dakimakura, cosplay, dark, crossover, light, night, guro, realistic, photo, real, landscape/scenery, cityscape, science_fiction, original, parody, personification, checkered, highres, lowres, absurdres, column_lineup, everyone, expressions, profile, bust, back, sample, album, covr, silhouette, what, artist_request, tagme, bad_id, watercolor_(medium), traditional_media, translation_request, Japanese, sketch, fine_art_parody, French, optical_illusion, zoom_layer, colorful, monochrome, gradient_background, pixel_art, wallpaper, simple_background, huge_filesize, incredibly_absurdres, transparent_background,- 角色常用：
girl, little boy, shota, loli, kawaii, mesugaki, adorable girl, bishoujo, sisters, gyaru, ojousama, mature female, mature, female pervert, milf, harem, angel, cheerleader, chibi, crossdressing, devil, doll, elf, fairy, female, furry, orc, giantess, harem, idol, kemonomimi_mode, loli, magical_girl, male, maid, mermaid, miko, milf, minigirl, monster, multiple_girls, no_humans, ninja, nun, nurse, shota, stewardess, student, trap, vampire, waitress, witch, yaoi, yukkuri_shiteitte_ne, yuri,- Consider yourself :
easynegative, toony, dated, line art, flat colors
Chinese and English bilingual
- Commonly used reverse prompts
| reverse cue word | describe |
|---|---|
| nsfw | Not Safe/Suitable For Work is not suitable for pictures that appear in public |
| mutated hands and fingers | mutated hands and fingers |
| deformed | Malformation |
| bad anatomy | poor anatomy |
| disfigured | disfigured |
| poorly drawn face | bad face drawing |
| mutated | mutated |
| extra limb | extra limb |
| ugly | ugly |
| poorly drawn hands | poorly drawn hands |
| missing limb | missing limb |
| floating limbs | floating limbs |
| disconnected limbs | limb incoherence |
| malformed hands | deformed hand |
| out of focus | out of focus |
| long neck | long neck |
| long body | body length |
- Positive prompt words to improve image quality
| positive prompt | describe |
|---|---|
| HDR, UHD, 8K (HDR, UHD, 4K, 8K and 64K) | Words of quality like this can make a huge difference in improving the quality of a photo |
| best quality | best quality |
| masterpiece | masterpiece |
| Highly detailed | Draw more detailed details |
| Studio lighting | Adding studio lighting can add some nice texture to the image |
| ultra-fine painting | super fine painting |
| sharp focus | clear focus |
| physically-based rendering | physically based rendering |
| extreme detail description | extremely detailed characterization |
| Professional | Adding this word can greatly improve the color contrast and details of the image |
| Vivid Colors | Add vibrant colors to pictures that can add vibrancy to your images |
| Bokeh | Bokeh blurs the background and highlights the subject, like iPhone's portrait mode |
| (EOS R8, 50mm, F1.2, 8K, RAW photo:1.2) | Photographer's description of camera settings |
| High resolution scan | Give your photos the look of an old photo Give it a sense of age |
| Sketch | sketch |
| Painting | painting |
- Artistic style representation
Add the style of the corresponding type of painter to enhance the effect of our photos.
| Art style | artist |
|---|---|
| Portraits | Derek Gores, Miles Aldridge, Jean Baptiste-Carpeaux, Anne-Louis Girodet |
| Landscape | Alexander Bursido, Jacques-Laurent Agasse, Andreas Achenbach, Cuno Amiet |
| Horror | H.R.Giger, Tim Burton, Andy Fairhurst, Zdzislaw Beksinski |
| Anime | Makoto Shinkai, Katsuhiro Otomo, Masashi Kishimoto, Kentaro Miura |
| 科幻画（Sci-fi） | Chesley Bonestell, Karel Thole, Jim Burns, Enki Bilal |
| 摄影（Photography） | Ansel Adams, Ray Earnes, Peter Kemp, Ruth Bernhard |
| 概念艺术家（视频游戏）（Concept artists (video game)) | Emerson Tung, Shaddy Safadi, Kentaro Miura |
- 视角
多试，有些不一定有效
| 提示词 | 描述 |
|---|---|
| dynamic angle | 动态角度 |
| from the left | 从左侧视角 |
| from the right | 从右侧视角 |
| from above | 从上方 |
| from below | 从下面 |
| looking up | 从下往上看 |
| looking down | 从上往下看 |
| top down | 从正上方往下看 |
| side view up | 从侧面往上看 |
| side view down | 从侧面往下看 |
| subject look up | 从人物的角度往上看 |
| subject look down | 从人物的角度往下看 |
| ground view up | 在地面往上看 |
| ground view down | 在地面往下看 |
| panoramic view | 全景 |
| wide shot | 广角宽景 |
| wide-angle view | 广角 |
| aerial view | 空中俯瞰视图 |
| bird view | 在高处往下看 |
| bird’s-eye view | 鸟瞰视角 |
| worm’s eye view | 蚯蚓视角 |
| angled | 带有角度的视角 |
| low-angle view | 低角度视角 |
| top-down | 俯视视角 |
| zoomed in | 放大镜效果 |
| zoomed out | 缩小镜效果 |
| top-down view | 俯视 |
| high-angle view | 高角度视角 |
| eye level view/level gaze/straight gaze | 平视 |
| close-up view | 特写 |
| extreme close-up view | 极端特写 |
| 微距（macro） | 放大画面中的细节，让物体看起来更加清晰和详细 |
| 高空俯瞰（aerial） | 从高空向下俯瞰场景，可以呈现出不同的地形和建筑物的分布 |
| 多角度（multi-angle） | 从多个角度捕捉场景，可以在一个图像中显示多个视图 |
| 夜景（night） | 将场景呈现为黑暗中的亮点和阴影，营造出一种神秘的氛围 |
| 人物特写（portrait） | 突出人物的面部特征，使他们的表情和个性更加鲜明 |
| 模糊（blur） | 在图像中使用模糊效果，可以产生一种柔和和梦幻的效果 |
| 扭曲（distort） | 通过扭曲场景中的物体来创造出一种独特的视觉效果 |
| 高速运动（motion blur） | 通过捕捉高速运动物体的轨迹来呈现出一种动态的效果 |
- 主体远近
| 提示词 | 描述 |
|---|---|
| full body / full body shot | 全身 |
| bust / upper body / half body / cowboy shot | 半身 |
| close-up shot | 接近 |
- 光线
| 提示词 | 描述 |
|---|---|
| cinematic lighting | 电影光 |
| dynamic lighting | 动感光 |
- 视线
| 提示词 | 描述 |
|---|---|
| looking at viewer | 画面中的物体或人物在直接面对画面或观众 |
| looking at another | 两个角色正在相互交流或对视 |
| looking away | 看着别的方向，不直视对方 |
| looking back | 回头看 |
| looking up | 摄像机或观察者的视角调整为向上看 |
- 画风
| 提示词 | 描述 |
|---|---|
| (draw a simple black and white sketch of an object or scene, with bold outlines and no shading) / sketch / one-hour drawing challenge | 素描、草图、速写、手绘风（用第一句话是可行的） |
| photograph, photorealistic | 照片 |
| flat design style | 扁平风 |
| monochrome | 单色 |
| duotone | 双色，1.5版本就是黑白色，而xl版则可有其它颜色的双色~~ |
| chinese Shadow Puppets | 皮影戏 |
| silhouette style | 剪影 |
| black and white style | 黑白照，只有把剪影和黑白照同时使用才能出现期望的剪影风格，如果不对的话，扁平化和单色也可以结合进来 |
- 身体指定
表情
| 提示词 | 描述 |
|---|---|
| blush | 脸红 |
| wet sweat | 大汗 |
| flying sweatdrops | 飞汗 |
- 衣服指定
制服
| 提示词 | 描述 |
|---|---|
| china dress | 旗袍 |
| sailor dress | 水手服 |
| school uniform | 校服 |
| sailor senshi uniform | 《美少女战士》中战士们穿着的制服，水手服 |
| 不多说了。。。 |
- 风景指定
| 提示词 | 描述 |
|---|---|
| underwater | 水下 |
| shinto shrine | 神社 |
- 姿势指定
| 提示词 | 描述 |
|---|---|
| hands on | 例hands on own face, hands on feet, hands on breast |
| kneeling | 跪下 |
| hand between legs | 腿夹手 |
| hair flip | 将头发向后或向一侧甩动的动作 |
| skirt flip | 裙子甩起来 |
- 通用风格（Midjourney）
使用及样稿可参考置顶文章《AI绘图风格对照表/画风样稿详细研究记录及经验总结》
| 提示词 | 描述 | SD可用 |
|---|---|---|
| holographic iridescent | 全息彩虹色 | holographic iridescent |
| Cyberpunk | 赛博朋克 | |
| Ukiyoe | 浮世绘 | |
| Blender 3d | 搅拌机3d渲染 | |
| Knolling | 摆拍 | |
| isometric 3d cube | 等距3D模型 | |
| 8bit/16bit pixel | 像素风 | pixel art |
| stick figure | 简笔画风格 | |
| Design a Sticker | 贴纸化 | |
| fluorescent | 荧光颜料 | |
| Embroidery Art | 刺绣艺术 | |
| paper cut craft | 剪纸艺术 | |
| Layered Paper | 折纸艺术 | |
| plasticine | 橡皮泥风格 | |
| Chinese ink style | 水墨画 | |
| chinese Shadow Puppets | 皮影戏艺术 | |
| Tilt-shift photography | 移轴摄影风格 | |
| Graffiti art, 2d, illustration | 平面涂鸦风格 | |
| Fairy Kei fashion | 仙女系 | |
| surrealism | 超现实主义 | |
| GENESIS | Genesis | |
| subconsciousness | subconscious | |
| romantic | romanticism | |
| Gothic Architecture and Landscape | Gothic landscape and architecture | |
| studio ghibli | Hayao Miyazaki style | |
| MARIO-STYLE | mario style | |
| pixel style | Pixar style | |
| minecraft | minecraft style | |
| out of LEGO | Lego blocks | |
| multiple views | Multi-view/Three-view |
Reference:
Stable Diffusion Prompt Usage
AI Painting Keywords Website Recommendation: Get Millions of Prompt Words Easily! Completely free
Stable Diffusion Affix Usage Specifications / Spell Chanting Guide (personal note sharing)
[Stable Diffusion] Prompt
(Getting Started) How to write Stable Diffusion prompt?
Official website: InstructPix2Pix
35 pictures, intuitive understanding of Stable Diffusion