{"id":15525,"date":"2024-07-13T12:48:26","date_gmt":"2024-07-13T04:48:26","guid":{"rendered":"https:\/\/www.1ai.net\/?p=15525"},"modified":"2024-07-13T12:49:19","modified_gmt":"2024-07-13T04:49:19","slug":"%e6%97%a0%e9%9c%80%e6%a8%a1%e7%89%b9%ef%bc%8c%e7%94%a8stable-diffusion%e4%bd%8e%e6%88%90%e6%9c%ac%e7%94%9f%e6%88%90ai%e6%9c%8d%e8%a3%85%e6%a8%a1%e7%89%b9%e5%9c%ba%e6%99%af%e5%9b%be","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/15525.html","title":{"rendered":"No need for models, use Stable Diffusion to generate AI clothing model scene images at low cost"},"content":{"rendered":"

This tutorial mainly uses Stable Diffusion<\/a> This tool is used to operate. How can we use Stable Diffusion to assist us in completing the model effect display? This tutorial is suitable for e-commerce design scenes, photography scenes and other actual combat using character design. The whole process is practical and requires everyone to absorb it slowly. After learning it, you can easily control the model's outfit change. Let's go!<\/p>\n

Vincent Figure<\/strong><\/p>\n

Libulibu is generated online. First use Wenshengtu, open the website, follow the rhythm, and start making<\/p>\n

https:\/\/www.liblib.art\/sd<\/p>\n

This tutorial is written in order from top to bottom.<\/p>\n

\u2460 Select the large model, \u2461 Enter keywords, \u2462 Set the drawing parameters, \u2463 Set ControlNet<\/p>\n

1. Choose a good large model<\/strong><\/p>\n

Large Model: Maiju Realism<\/p>\n

Large models can be searched here, just click to add to the model library<\/p>\n

https:\/\/www.liblib.art<\/p>\n

\"get-443\"<\/div>\n

2. Enter keywords<\/strong><\/p>\n

SD keywords are divided into positive and negative<\/p>\n

Positive keywords:<\/p>\n

Half of a beautiful woman,Outdoor,background with sky,White halter dress,long black hair,The wind blows the hair,hair flowing,best quality,masterpiece,eyes closed,breeze blowing hair,background blurred,5 fingers,Natural light, blue sky, sky with no other object<\/p>\n

Half-length portrait of a beautiful woman, outdoors, sky background, white suspender dress, long black hair, wind blowing her hair, flowing hair, best quality, masterpiece, closed eyes, breeze blowing her hair, blurred background, 5 fingers, natural light, blue sky, sky with no other objects<\/p>\n

Negative keywords:<\/p>\n

ng_deepnegative_v1_75t,(badhandv4:1.2),EasyNegative,(worst quality:2),easynegative,drawing,painting,crayon,sketch,graphite,impressionist,noisy,blurry,soft,deformed,ugly,(deformed iris, deformed pupils, semi- realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4),text,close up,cropped,out of frame,worst quality,low quality,jpeg artifacts,ugly,duplicate,morbid,mutilated,extra fingers, mutated hands,poorly drawn hands,poorly drawn face,mutation,deformed,blurry,dehydrated,bad anatomy,bad proportions,extra limbs,cloned face,disfigured,gross proportions,malformed limbs,missing arms,missing legs,extra arms,extra legs,fused fingers,too many fingers,long neck,((nsfw)),sketches,tattoo,(beard:1.3),(EasyNegative:1.3),badhandv4,(worst quality:2),( low quality:2),(normal quality:2),lowers,normal quality,facing away,looking away,text,error,extra digit,fewer digits,cropped,jpeg artifacts,signature,watermark,username,blurry,skin spots, acnes,skin blemishes,bad anatomy,fat,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,tilted head.bad anatomy.bad hands,extra fingers,fewer digits,extra limbs.extra arms,extra legs ,malformed limbs.fused fingers,too many fingers,long neck,cross-eyed,mutated hands,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,missing legs,extra digit,extra arms,extra leg,extra foot,missing fingers,(Worst quality,low quality,lowres:1.2) ,error,cropped,jpeg artifacts,out of frame,watermark,signature<\/p>\n

ng_deepnegative_v1_75t, (badhandv4:1.2), EasyNegative, (worst quality:2), EasyNegative, drawing, painting, crayon, sketch, graphite, impressionist, noise, blur, soft, distorted, ugly, (distorted iris, distorted pupil, semi-realistic, cgi, 3d, render, sketch, cartoon, painting, animation:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, sick, mutilated, extra fingers, mutant hand, badly drawn hand, badly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, thick proportions, deformed limbs, missing arm, missing leg, extra arm, extra leg, fused fingers, too many fingers, long neck, ((ns fw), sketch, tattoo, (beard: 1.3), (EasyNegative: 1.3), badhand 4, (worst quality: 2), (low) quality: 2), (normal quality: 2), low, normal quality, facing away, looking away, text, error, extra digits, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, skin spots, acne, skin blemishes, bad anatomy, fat, bad feet, cropped, badly drawn hands, badly drawn face, mutation, deformed, tilted head. bad anatomy. bad hands, too many fingers, too few fingers, too many limbs. extra arms, extra legs, misshapen limbs. fused fingers, too many fingers, long neck, crossed eyes, mutant hands, bad body, bad proportions, thick proportions, text, errors, missing fingers, missing arms, missing legs, extra fingers, extra arms, extra legs, extra feet, missing fingers, (worst quality, low quality, low resolution: 1.2), errors, cropped, jpeg artifacts, out of frame, watermark, signature<\/p>\n

3. Set the drawing parameters<\/strong><\/p>\n

Sampling method: DPM++ 2M Karras<\/p>\n

Iterations: 30<\/p>\n

Check High Resolution Repair<\/p>\n

Amplification algorithm: 4x-UltraSharp<\/p>\n

Redraw sampling steps: 20<\/p>\n

Redraw amplitude: 0.4<\/p>\n

Proportional scaling: 2<\/p>\n

Number of pictures: 3 (you can add more if the effect test is satisfactory)<\/p>\n

Prompt word<\/a>Guidance factor: 7<\/p>\n

\"get-444\"<\/div>\n

4. Set up ControlNet<\/strong><\/p>\n

Upload the reference image here and check Enable<\/p>\n

ControlNet chooses OpenPose to fix character poses<\/p>\n

Preprocessor selection: dw_openpose_full<\/p>\n

Model selection: control_v11p_sd15_openpose<\/p>\n

Control weight: 1<\/p>\n

Starting steps: 0<\/p>\n

Steps completed: 1<\/p>\n

\"get-445\"<\/div>\n

Upload the reference image here and check Enable<\/p>\n

ControlNet selects the Depth map to control the finger<\/p>\n

Preprocessor selection: depth_hand_refiner<\/p>\n

Model selection:<\/p>\n

control_sd15_inpaint_depth_hand_fp16<\/p>\n

Control weight: 1<\/p>\n

Starting steps: 0<\/p>\n

Steps completed: 1<\/p>\n

\"get-446\"<\/div>\n

Once everything is done, you can start generating images. View the generated images in the gallery.<\/p>\n

\"get-447\"<\/div>\n

I looked through a lot of pictures here, trying to make the fingers look good in one go, but the result did not meet my requirements, so I decided to choose one with similar effect first, and then retouch the hands in the raw picture.<\/p>\n

\"get-450\"<\/div>\n

Figure 1<\/strong><\/p>\n

Now I start using the image generation function, the main purpose is to repair the hand<\/p>\n

\u2460 Select the large model, \u2461 Enter keywords, \u2462 Select the LORA model, \u2463 Upload the image, \u2464 Set the output parameters, \u2465 Set ControlNet<\/p>\n

1. Choose a good large model<\/strong><\/p>\n

Large Model: Maiju Realism<\/p>\n

Large models can be searched here, just click to add to the model library<\/p>\n

https:\/\/www.liblib.art<\/p>\n

\"get-448\"<\/div>\n

2. Enter keywords<\/strong><\/p>\n

Positive keywords:<\/p>\n

Hands,good-looking hands,perfect hands,(five fingers:1.1),(Nails intact:1.1),finger repair,Finger optimization,repair Hand optimization,complete repair<\/p>\n

Hands, beautiful hands, perfect hands, (five fingers: 1.1), (intact nails: 1.1), finger repair, finger optimization, repair hand optimization, complete repair<\/p>\n

Negative keywords:<\/p>\n

Deformed,deformed hands,four fingers,six fingers<\/p>\n

Deformed, deformed hand, four fingers, six fingers<\/p>\n

3. Choose a good LORA model<\/strong><\/p>\n

Click Add<\/p>\n

Model 1: Hand Optimization - Hand repair is fine, weight is 0.8<\/p>\n

LORA models can be searched here, just click to add to the model library<\/p>\n

https:\/\/www.liblib.art<\/p>\n

\"get-449\"<\/div>\n

4. Upload pictures<\/strong><\/p>\n

Upload the image saved in the Wenshengtu to the Shengtu \u2192 Partial Redraw, and use the brush to blacken the hand area<\/p>\n

Mask Mode: Redraw the mask content<\/p>\n

\"get-450\"<\/div>\n

5. Set the drawing parameters<\/strong><\/p>\n

Sampling method: DPM++ 2M Karras<\/p>\n

Iterations: 25<\/p>\n

Resize: 1.3 times<\/p>\n

Number of images: 3<\/p>\n

Prompt word guidance coefficient: 7<\/p>\n

Redraw step: 1<\/p>\n

\"get-454\"<\/div>\n

6. Set up ControlNet<\/strong><\/p>\n

Upload the pictures saved in Wenshengtu here and check Enable<\/p>\n

ControlNet chooses OpenPose to fix character poses<\/p>\n

Preprocessor selection: dw_openpose_full<\/p>\n

Model selection: control_v11p_sd15_openpose<\/p>\n

Control weight: 1<\/p>\n

Starting steps: 0<\/p>\n

Steps completed: 1<\/p>\n

\"get-451\"<\/div>\n

Upload the pictures saved in Wenshengtu here and check Enable<\/p>\n

ControlNet selects the Depth map to control the finger<\/p>\n

Preprocessor selection: depth_hand_refiner<\/p>\n

Model selection:<\/p>\n

control_sd15_inpaint_depth_hand_fp16<\/p>\n

Control weight: 0.65<\/p>\n

Starting steps: 0<\/p>\n

Steps completed: 1<\/p>\n

\"get-452\"<\/div>\n

Once everything is done, you can start generating images. View the generated images in the gallery.<\/p>\n

\"get-455\"<\/div>\n

The process of hand-editing is to continuously generate pictures that feel good, and then run the pictures again and again according to the process of picture generation and partial redrawing until the effect is satisfactory. To be honest, I am not very satisfied with the final picture, but I don\u2019t want to draw cards anymore, so I decided to use PS to revise it.<\/p>\n

\"get-453\"<\/div>\n

PS Post<\/strong><\/p>\n

\u2460 Make the characters look better; \u2461 Add the product and handle the light and shadow; \u2462 Add the copy<\/p>\n

Although the hands still don't look very good, the production process is like this. It depends on your patience. Use SD to slowly brush the pictures and PS to slowly edit them.<\/p>\n

\"get-456\"<\/div>\n

Okay, this sharing ends here.<\/p>","protected":false},"excerpt":{"rendered":"

This tutorial mainly use Stable Diffusion this tool to operate, how we should use Stable Diffusion to assist us to complete the model effect show. This tutorial applies to e-commerce design scenes, photography scenes and other multiple use of character design in practice, the whole dry goods, need to be slowly absorbed, after learning to easily pinch the model to dress, let's go! art\/sd This tutorial is written in the order of top-to-bottom operation \u2460 Select a large model, \u2461 Enter keywords, \u2462 Set the parameters of the map, \u2463 Set ControlNet<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[149,144],"tags":[491,197,3483,198,837],"collection":[302,262],"class_list":{"0":"post-15525","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"hentry","6":"category-jiaocheng","7":"category-baike","8":"tag-ai","9":"tag-stable-diffusion","12":"tag-837","13":"collection-prompt","14":"collection-stablediffusion"},"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15525","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=15525"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15525\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=15525"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=15525"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=15525"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=15525"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}