Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

Today I would like to share with you a 2.5D model trained based on the Pony model: Speciosa 2.5D.

Speciosa is a Latin word meaning "beautiful", so the model is good at generating semi-realistic cute Korean girls. The overall quality of the pictures generated by the model is excellent, the skin of the beauties is delicate, and very high-quality pictures can be produced without the need for an enlargement algorithm.

On the official website, the author provides the model training method

Step #1: Js2Prony(v1.0) *0.35 + DucHaiten-Pony-XL(pony-no-score_v4.0)* 0.65 and merge loraPony Realistic Tweaker(v1.0-rev3)* 0.6 to get the first model result 1.safetensor.

Step #2: Result 1* 0.6 + Speciosa Realistica(v1.2) * 0.4 = Speciosa 2.5D(v1.2).

Model download address (you can also get the network disk address at the end of the article)

LiblibAI: https://www.liblib.art/modelinfo/32628cae263547a29a87f75a8b22a1bc

Station C:https://civitai.com/models/560402

Let's actually experience it and see how the pictures produced by using this model look like.

ReversePrompt word

score_6,score_5,score_4,source_pony,(worst quality:1.2),(low quality:1.2),(normal quality:1.2),lowres,bad anatomy,bad hands,signature,watermarks,ugly,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,extra limb,missing limbs,painting by bad-artist

Common parameter settings

  • Large model: Speciosa 2.5D V1.2
  • Sampler: DPM++ 2M Karras
  • Sampling iteration number: 28
  • CFG: 7
  • Image width and height: 768*1024 (864x1280)
  • Open the After Detailer plug-in and select face_yolov8n as the model

1. Long-haired girl

Prompt:score_9,score_8_up,score_7_up,8k,UHD,1 beautiful girl,20 years old,black hair,very long hair,straight hair,closed mouth,detailed face,beautiful woman's face,sweater,red background,looking at viewer

Prompt words: 1 beautiful girl, 20 years old, black hair, long hair, straight hair, closed mouth, delicate face, beauty face, sweater, red background, looking at the viewer

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

2. Colored Hair

Prompt:score_9, score_8_up, score_7_up, film grain, photo by fuji-proplus-ii film, raw picture of 20 years old girl in black sweater, portrait, colored hair, outdoor, deep blue sky, cloudy sky, fiery clouds,high key light , soft shadow

Prompt word: Film grain, shot with Fuji ProPlus-II film, original photo of 20-year-old girl in black sweater, portrait, colored hair, outdoors, dark blue sky, cloudy sky, fiery red clouds, highlights, soft shadows

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

3. Jeans

Prompt:score_9,score_8_up,score_7_up,8k,UHD,1 super beautiful girl,solo,20 years old,detailed face,black hair,short hair,full body,pantyhose,high heeled boots,sweater,jeans short,looking at viewer,white background

Prompt word: 1 super beautiful girl, detailed face, black hair, short hair, full body, stockings, high-heeled boots, sweater, jeans, looking at the viewer, white background

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

4. Black tights

score_9, score_8_up, score_7_up, score_6_up, 8k,UHD, 1 super beautiful girl, red eyes, makeup, eyeliner, eyeshadow, mascara, black background, black bodysuit, perfect female waist, suggestive pose, dynamic pose, moonlight,halftone lighting, detailed drawing (perfect hands, perfect fingers) ,side view, perfect lighting, perfect shadows

Prompt word: 1 super beautiful woman, red eyes, makeup, eyeliner, eyeshadow, eyelashes, black background, black tights, perfect female waist, suggestive pose, dynamic pose, moonlight, halftone lighting, detailed drawing (perfect hands, perfect fingers), side view, perfect lighting, perfect shadows

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

5. Library

Prompt:score_9,score_8_up,score_7_up,score_6_up,8k,UHD,1 super beautiful girl,long hair,black hair,holding cellphone,looking at the cellphone,front view,library,sitting by a desk,book on desk,rim light,background light

Tips:1 super beautiful girl, long hair, black hair, holding a mobile phone, looking at the phone, front view, library, sitting at the table, books on the table, edge light, background light

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

6. Policewoman

Prompt:score_9,score_8_up,score_7_up,score_6_up,8k,UHD,1 super beautiful policewoman,solo,black necktie,hat,blue shirt,blue skirt,black pantyhose,short sleeves,red background

Tips:1 super nice policeman, single, black tie, hat, blue shirt, blue skirt, black pantyhose, short sleeves, red background

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

7. Beauty and the Castle

Prompt:score_9,masterpiece,best quality,1 super beautiful girl,solo,black hair,long hair,(grin:1.2),jewelry,earrings,hair ornament,red lips,collarbone,full body,in winter,castle

Tips:Masterpiece, best quality, 1 super beautiful girl, solo, brunette, long hair, (smile: 1.2), jewelry, earrings, hair accessories, red lips, collarbone, full body, winter, castle

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

8. Girl at Sunset

Prompt:score_9,score_8_up,score_7_up,score_6_up,8k,UHD,film grain,photo by fuji-proplus-ii film,raw photo of 20 years old girl,veil hat,hanfu,standing,full body,outdoor,deep blue sky,cloudy sky ,high key light,soft shadow,sunset

Tips:Film texture, shot with Fuji Proplus-II film, original image of a 20-year-old girl, veil hat, Hanfu, standing, full body, outdoors, dark blue sky, cloudy sky, highlights, soft shadows, sunset

Stable Diffusion model recommendation, a semi-realistic/2.5D style AI painting model

Okay, that’s all for today’s sharing. I hope that what I shared today will be helpful to you.

The model is placed in the network disk, and those who are interested can take it!

https://pan.quark.cn/s/b3df771404e2

 

statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
TutorialEncyclopedia

Download and install the largest open source Wenshengtu model FLUX, and enjoy the stunning pictures directly from the Dev version

2024-8-4 10:08:57

TutorialEncyclopedia

How to use AI drawing, i.e. Dream AI generates cartoon character sets with high character consistency and multiple expressions and actions

2024-8-6 11:57:09

Search