tag如下，模型下載地址

https://civitai.com/models/4451/abyssorangemix2-hardcore 橘子

https://civitai.com/models/6424/chilloutmix? ?寫實

https://civitai.com/models/7537/glorious-azure-lane-spring 光榮lora

https://civitai.com/models/5414/pastel-mix-stylized-anime-model? 蠟筆

realistic,skin pores,masterpiece,best quality,full body,
1girl,solo, <lora:[Glorious]Spiring:1>,blonde hair,kimono, bare shoulders, cleavage,holding up, kneel
Negative prompt: (nsfw),(animated, cartoon, painting, drawing, comic),((blurry)), (ugly:1.3), duplicat, (worst quality, low quality:1.3), obese, fat, plump, huge , gigantic
Steps: 33, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 983843330, Size: 500x500, Model hash: 3d281e3bb6, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: gloriousAzureLaneSpring_GloriousSpiring(e558252f5673), AddNet Weight A 1: 1, AddNet Weight B 1: 1, AddNet Module 2: LoRA, AddNet Model 2: taiwanDollLikeness_v10(aa12327d4bab), AddNet Weight A 2: 0.2, AddNet Weight B 2: 0.2, Hires upscale: 2, Hires upscaler: Latent

tag是死的人是活的，在tag里隨便加內(nèi)容，比如森林，小溪，野餐，坐在地上，就可以畫出下面野餐的那些圖，其他的各位可以自己嘗試，想畫啥就畫啥，第一行質(zhì)量tag固定不動就行，同理，你下了其他人的lora模型，也能直接用，換相應描述詞就行。

用chill模型融一下橘子，比例7:3，加光榮涼夜香雪lora，vae用chill作者推薦的那個就行，就8400那個

蠟筆模型加橘子融，一比一就行，加光榮涼夜香雪lora，vae用蠟筆

進階版

nsfw,realistic,skin pores,masterpiece,best quality,full body,
,1girl,solo,Lie down,nude,blonde hair,kimono, cleavage, look at the camera, smile,Indoor, chest, nipple, collarbone, belly, blush, sexy, slutty,Japanese-style room,(corneo_side_deepthroat),
Negative prompt: ((nsfw)),(animated, cartoon, painting, drawing, comic),((blurry)), (ugly:1.3), duplicat, (worst quality, low quality:1.3), obese, fat, plump, huge , gigantic
Steps: 39, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 20475711, Size: 500x650, Model hash: 3d281e3bb6, Denoising strength: 0.5, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: gloriousAzureLaneSpring_GloriousSpiring(e558252f5673), AddNet Weight A 1: 0.8, AddNet Weight B 1: 0.8, AddNet Module 2: LoRA, AddNet Model 2: taiwanDollLikeness_v10(aa12327d4bab), AddNet Weight A 2: 0.2, AddNet Weight B 2: 0.2, Hires upscale: 2, Hires upscaler: Latent

不多解釋，自己試試吧? ?需要這個emb? https://civitai.com/models/5371/corneos-side-view-deepthroat-ti-embedding