Create

DucHaiten-Niji-SDXL

CHECKPOINT
Original


Updated:

blur image
masterpiece, best quality, half body, portrait, night city, 1girl, anime, 3D, Japan, pixar, realistic, teen girl, smiling, cute face, harajuku fashion style, rain coat, beautiful, colourful, neon lights, cyberpunk, smooth skin, illustration, by stanley artgerm lau, sideways glance, foreshortening, extremely detailed 8K, smooth, high resolution, ultra quality, highly detail eyes, highly detail mouth, highly detailed face, perfect eyes, both eyes are the same, glare, Iridescent, Global illumination, hd, 8k realistic light and shadow, bright Eyes, fluorescent eyes
  • masterpiece, best quality, half body, portrait, night city, 1girl, anime, 3D, Japan, pixar, realistic, teen girl, smiling, cute face, harajuku fashion style, rain coat, beautiful, colourful, neon lights, cyberpunk, smooth skin, illustration, by stanley artgerm lau, sideways glance, foreshortening, extremely detailed 8K, smooth, high resolution, ultra quality, highly detail eyes, highly detail mouth, highly detailed face, perfect eyes, both eyes are the same, glare, Iridescent, Global illumination, hd, 8k realistic light and shadow, bright Eyes, fluorescent eyes
  • Realistic style, Lily, forever haunted by her mother's presence, finds no solace as she encounters her mother's twisted face in every reflective surface, leaving her in a perpetual state of fear, hyperdetailed, 8k, hyperrealistic,
  • A female realistic portrait gothic skull character with buns hair and wearing a magenta gothic outfit, big skull cap, standing next to neon motercycle coming out of the gate of skulls, in the style of gothic dark and macabre, 2d game art, flurocescent colours, strong facial expression, cinematic lighting, chinapunk, violent, rtx on, eye - catching, black paintings, in the style of Artgerm
  • A female realistic portrait gothic skull character with buns hair and wearing a magenta gothic outfit, big skull cap, standing next to neon motercycle coming out of the gate of skulls, in the style of gothic dark and macabre, 2d game art, flurocescent colours, strong facial expression, cinematic lighting, chinapunk, violent, rtx on, eye - catching, black paintings, in the style of Artgerm
  • Realistic painting of chest shot portrait of a red hair young man in black military uniform holding a whip in hand with evil smile, high angle view, floral arrangement, leather, elegant, alfons mucha, art nouveau - inspired illustration, art deco, dreamlike figures, oshare kei, visual kei, red and dark black, dark background, hyper - realistic details, detailed character illustrations, 8k, ultra hd, ultra detailed
  • Long straight black bang hair, evangelion, school girl, menhera, japan, gloomy face, depress, smiling, insane,
  • Realistic film still of Aino Minako smiling in magical battle form from live action film of ‘ Sailor Moon’, a beautiful japanese girl with a red bow on long flowing blonde hairs, wear white navy blue striped sailor school uniform with red sailor necktie, blue eyes
  • Mai Shiranui,女孩,旗袍,Dream, cute girl on a red hoodie, in the style of yuumei, realistic hyper - detailed rendering, yumihiko amano, zhang jingna, wiccan, trace monotone, rtx on ,細緻的背景
  • Mai Shiranui,女孩,旗袍,Dream, cute girl on a red hoodie, in the style of yuumei, realistic hyper - detailed rendering, yumihiko amano, zhang jingna, wiccan, trace monotone, rtx on ,細緻的背景

Strangely, sdxl cannot create a single style for a model, it is required to have multiple styles for a model. Over-multiplication is the problem I'm having with the sdxl model. Initially I just wanted to create a Niji3d model for sdxl, but it only works when you don't add other keywords that affect the style like realistic, photo, realism, artist name, drawing style...etc. So I decided to change from Niji's 3D-only model to an even more diverse model.

Negative prompt:

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist

SDXL usage is completely different from all previous models:

1/ the number of cfg is greatly affected, can replace clip skip. if you want to create surreal images cfg 3-4 or 5 is suitable, cartoon or 3d character images should be clear, cfg should be 6-7, and real people photos can sometimes be up to 7-8, but only if you need high precision and detail to get cfg up to 9-10 or higher, I haven't tried it yet.

2/ the number of steps also has a much greater influence on the results, the image only starts to achieve high quality when it is 50 steps or more. Right now I don't know where its limit is, it's like the higher the step count, the better the image. Of course it can be different when changing styles, changing models, or even changing samplers. I still can't try it all.

3/ the way to get prompts will be different from other sd models, but I don’t know how, just feel that the prompts are too cumbersome and not as good as before and instead of writing in tag style, You can try to choose a descriptive writing style like Midjourney

4/ SDXL it seems that the more data, the less keywords are needed in prompt and negative prompt.

5/ That's all for now, I'll keep updating as new information or changes become available, anyway it's new technology for all of us.

If you like my content, support me at: https://linktr.ee/Duc_Haiten

104,191
Runs
112
Downloads
Uploaded
Base ModelSDXL 1.0
  • Download the model file

  • Use without crediting

  • Share merges of this model

  • Use different permissions on merges

Commercial use: Sell generated images

Comments

Related Posts