S：AI能取代設(shè)計(jì)師么？
I ：至少在設(shè)計(jì)行業(yè)，目前AI扮演的主要角色還是超級(jí)工具，要頂替？除非甲方對(duì)設(shè)計(jì)效果無(wú)所畏懼~~

---

預(yù)先學(xué)習(xí)：

• 安裝及其問(wèn)題解決參考：《Windows安裝Stable Diffusion WebUI及問(wèn)題解決記錄》；
• 運(yùn)行使用時(shí)問(wèn)題《Windows使用Stable Diffusion時(shí)遇到的各種問(wèn)題整理》；
• 模型運(yùn)用及參數(shù)《Stable Diffusion 個(gè)人推薦的各種模型及設(shè)置參數(shù)、擴(kuò)展應(yīng)用等合集》；
• 提示詞生圖咒語(yǔ)《AI繪圖提示詞/咒語(yǔ)/詞綴/關(guān)鍵詞使用指南（Stable Diffusion Prompt 設(shè)計(jì)師操作手冊(cè)）》；
• 不同類(lèi)的模型Models說(shuō)明《解析不同種類(lèi)的StableDiffusion模型Models》；
• 繪制人物動(dòng)作及手腳細(xì)節(jié)《Stable Diffusion 準(zhǔn)確繪制人物動(dòng)作及手腳細(xì)節(jié)（需ControlNet擴(kuò)展）》；
• 各種風(fēng)格對(duì)比及實(shí)際運(yùn)用《AI繪圖風(fēng)格對(duì)照表/畫(huà)風(fēng)樣稿詳細(xì)研究記錄及經(jīng)驗(yàn)總結(jié)》；

stable diffusion就只能小姐姐么？不，今天我們用stable diffusion對(duì)三種建筑方面的圖片進(jìn)行修改。

一、渲染室內(nèi)設(shè)計(jì)線稿圖

成圖目標(biāo)

網(wǎng)上弄來(lái)一張線稿，要求貼色貼材質(zhì)，盡量追求與線稿中物體接近。

物品一目了然，就不多說(shuō)了。

線稿導(dǎo)入controlnet

邊緣檢測(cè)權(quán)重1

線條檢測(cè)權(quán)重0.9

深度檢測(cè)權(quán)重0.8，可以不用

這張圖里如果沒(méi)有邊緣檢測(cè)，左下角的電視機(jī)柜往往出現(xiàn)一堆書(shū)

提示詞及渲染出圖

• 盡量將每個(gè)位置的內(nèi)容都提到，這樣才可能盡可能相似；
• 注意提示詞相關(guān)性設(shè)置得可以高一點(diǎn)，比如這里是22

((photorealistic)), 8k, clean room, sunlight, white ceiling, blue curtains, red sofa, yellow cabinet, wooden bed, Persian carpet under bed, bed end bench, wooden floor,
lower left corner is low cabinet, upper left corner is wall, upper right corner is windows and tatami, the wall above the head of the bed is made of wood, desk lamp on the nightstand to the right of the bed
Negative prompt: low res,text,error,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,text font ui,futa,yaoi,
Steps: 20, Sampler: Euler a, CFG scale: 22,

出圖基本符合設(shè)計(jì)稿結(jié)構(gòu)，小修改用圖生圖里的局部重繪，這里不再贅述，可參考下面景觀調(diào)整操作。

二、調(diào)整景觀設(shè)計(jì)手繪稿部分元素

成圖目標(biāo)

根據(jù)要求修改效果圖中部分元素，加入人物和水中活物

修改元素

用局部重繪方式增加成年人元素，注意：

• 水彩風(fēng)格前先使用物體邊緣線條，否則可能與原圖不符
• 同時(shí)重繪區(qū)域選擇僅蒙版，這樣可以讓人物不會(huì)畫(huà)壞了

 ((object edge line)),((watercolor painting)),1male walking on flagstone path, green grass, blue pond, full body,
 Negative prompt: ((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

其它提示詞不變，修改為小孩，注意這個(gè)蒙版不能太小，否則小孩動(dòng)作施展不開(kāi)容易缺胳膊少腿。

 ((object edge line)),((watercolor painting)),1child walking on flagstone path, green grass, blue pond, full body,

增加魚(yú)

((object edge line)),((watercolor painting)),kois in blue pond,

出圖修補(bǔ)

基本算定型了，小修改和上面操作一樣，不贅述。
大家有沒(méi)有發(fā)現(xiàn)，類(lèi)似這種風(fēng)格的稿子，如果是在繪圖軟件里做的，其實(shí)讓原作者直接修改來(lái)得更快更準(zhǔn)確。

三、改建筑照片為線稿

這是用PS修改的線稿圖，可以參考一下：《用PS將一張照片調(diào)成簡(jiǎn)筆畫(huà)風(fēng)格》

選擇照片

把線條風(fēng)格先提示了。

((a line drawing, line art, line work)), simple line, black AND white, buildings, street, trees, cars, street light
negative prompt: colorful

圖生圖

先將一張空白圖片放入圖生圖

將照片放入controlnet中，使用相關(guān)模式生成線條，注意優(yōu)先選擇controlnet is more important測(cè)試。

模型可用lineart、canny、mlsd、depth等，但具體用哪個(gè)需要自己試驗(yàn)，不同的圖片最終效果不同，比如此圖用lineart_realistic找建筑線條就比用canny描繪更準(zhǔn)確和精煉，canny描繪出細(xì)節(jié)太多，按照線稿要求看就太雜了。

線稿對(duì)比

對(duì)比一下不同重繪幅度的區(qū)別，這種模式下，0.82~0.90最合適。

下面各張對(duì)比圖的重繪幅度、種子、模型、提示詞等都有略微調(diào)整，畫(huà)面按照由濃到淡排列。

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful
Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 199447306, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.9, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: canny, ControlNet-0 Model: control_v11p_sd15_canny [d14c016b], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black line, white background, high contrast, buildings, street, trees, cars, street light
Negative prompt: colorful, gray
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 847333786, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.9, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 1879644544, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.85, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black line, sketch, white background, high contrast, buildings, street, trees, cars, street light
Negative prompt: color
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 1607122200, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.84, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black line, white background, high contrast, buildings, street, trees, cars, street light
Negative prompt: colorful, gray
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 2330278839, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.84, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black line, white background, high contrast, buildings, street, trees, cars, (white ground),
Negative prompt: colorful, gray,
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 3402894627, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.84, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black line, white background, high contrast, buildings, street, trees, cars, street light
Negative prompt: colorful, gray
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 167399156, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.84, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Steps: 64, Sampler: Euler a, CFG scale: 22, Seed: 1994739401, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.8, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_lineart [43d4be0d], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful, gray
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 4145571130, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.85, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: mlsd, ControlNet-0 Model: control_v11p_sd15_mlsd [aca30ff0], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful, gray
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 3008838972, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.85, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: depth_zoe, ControlNet-0 Model: control_v11f1p_sd15_depth [cfd03158], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

下面兩張由ai自己發(fā)揮，僅提示詞配了線條畫(huà)詞綴，出圖相比用了controlnet要更線稿。

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 178003217, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.85, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: depth_zoe, ControlNet-0 Model: coadapter-depth-sd15v1 [93aff3ab], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

a line drawing, line art, line work, black and white, buildings, street, trees, cars, street light
Negative prompt: colorful
Steps: 64, Sampler: Euler a, CFG scale: 7, Seed: 3853790227, Size: 1024x512, Model hash: a60cfaa90d, Model: dreamshaper_5BakedVae, Denoising strength: 0.9, Clip skip: 2, ENSD: 31337, ControlNet-0 Enabled: True, ControlNet-0 Module: lineart_realistic, ControlNet-0 Model: control_v11p_sd15_canny [d14c016b], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1

最后，大家學(xué)習(xí)過(guò)這篇內(nèi)容了么？AI繪圖實(shí)戰(zhàn)（六）：制作一張慶祝五一勞動(dòng)節(jié)的海報(bào) | Stable Diffusion成為設(shè)計(jì)師生產(chǎn)力工具文章來(lái)源地址http://www.zghlxwxcb.cn/news/detail-456234.html

到了這里，關(guān)于AI繪圖實(shí)戰(zhàn)（七）：室內(nèi)設(shè)計(jì)線稿渲染、景觀設(shè)計(jì)手繪稿改動(dòng)、建筑照片轉(zhuǎn)線稿｜Stable Diffusion成為設(shè)計(jì)師生產(chǎn)力工具的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！