SeaArt Guide
How to SeaArt AI - Office Tutorial
How to SeaArt AI - Office Tutorial
  • ✨How to Use an AI Image Generator
  • ✨1-SeaArt AI Basic Page
  • ✨2-SeaArt AI Basic Function
    • 2-1 Text to Image
    • 2-2 Image to Image
    • 2-3 ControlNet
    • 2-4 AI Apps
      • How to publish as App
      • Swift AI Apps
    • 2-5 AI Characters
      • How to create your own character?
      • Character Description Writing Tips
      • Conversation Tips
    • 2-6 Models
    • 2-7 Post
    • 2-8 AI Video Generation
      • Txt2Vid
      • Img2Vid
      • Camera Movement
      • Start and End Frames
    • 2-9 AI Audio
    • 2-10 Workflow
      • Text to Image Workflow
      • IMG2IMG+Partial Repainting
      • Core Nodes
      • Tips
    • 2-11 Canvas
    • 2-12 LoRA Training
      • Flux Lora Training
  • ✨3-Advanced Guide
    • 3-1 Principles of AI art
    • 3-2 LoRA Training (Advance)
      • How To Create Dataset For Training
    • 3-3 Workflow Guide
      • Image Conversion
      • Inpainting
    • 3-4 Canvas Guide
    • Composite Poster
  • ✨4-Parameters
    • 4-1 Model
    • 4-2 Mode
    • 4-3 Basic Settings
    • 4-4 Advanced Config
    • 4-5 Advanced Repair
    • 4-6 Complete Prompting Guide
    • 4-7 Prompt Edit | Keyword Blending Guide
  • ✨5-Practical Examples
    • AI Influencer
    • LOGO Design
    • E-commerce Poster
    • How To Make Multiple Characters
    • Prompt Templates
    • How to Maintain Character Consistency
    • Useful Prompts
  • ✨6-Permanent Events
    • SeaArt.AI Creator Incentive Program
      • Creator Incentive Program FAQ
    • High-Quality Models Recommendation
      • SeaArt Infinity
      • Stable Diffusion 3.5
      • SeaArt Realism
      • NOOBAI XL
      • T-Ponynai3 V6
      • Counterfeit V3.0
      • Temporal Paradox Mix
    • High-Quality AI Apps Recommendation
    • High-Quality Character Recommendation
    • High-Quality Workflow Recommendation
  • ✨7-FAQ
Powered by GitBook
On this page
  • Model Usage
  • Prompt
  • Prompt Template
  • Prompt Guidelines
  • Characters and Artists
  • Generation Parameters
  • Result Example
  1. 6-Permanent Events
  2. High-Quality Models Recommendation

NOOBAI XL

NOOBAI-XL specializes in anime image generation, replicating anime characters, artists' styles, and furry content with minimal use of Lora models.

PreviousSeaArt RealismNextT-Ponynai3 V6

Last updated 5 months ago

NOOBAI XL is based on the SDXL model architecture, with the Illustrious-xl-early-release-v0 as the base model. It has been trained on a large number of iterations using the complete Danbooru and e621 datasets (approximately 13,000,000 images), providing rich knowledge and excellent performance.

NOOBAI-XL is primarily used for anime image generation and is capable of reproducing the styles of thousands of anime characters and artists. It recognizes a wide range of unique concepts from the anime world and has extensive knowledge of furry content. It excels at generating tasks with minimal use of Lora models.

Try the Model:

Based on the NOOB model, it has a stable basic art style compared to NOOBCollaborate with NOOB artists to explore various composition angles and colors.

Model Usage

  • It is recommended to add aesthetic and quality tags before the prompt words. Aesthetic tags: very awa, worst aesthetic Quality tags: masterpiece > best quality > high quality / good quality > normal quality > low quality / bad quality > worst quality

  • The trigger word for a character is its character name; the trigger word for an artist's style is the artist's name

  • NoobAI-XL supports special tags such as quality, aesthetics, creation year, creation period, and safety level for auxiliary use.

Prompt

Prompt Template

Prompt: very awa, masterpiece, best quality, newest, highres, absurdres

Negative Prompt: NSFW, low quality, worst quality, normal quality, text, signature, jpeg artifacts, bad anatomy, old, early, copyright name, watermark, artist name, signature

Prompt Guidelines

  • It is recommended to use phrases, separated by ", ". For example: 1girl, solo, blue hair.

  • Prompts should not contain any underscores "_".

  • If necessary, escape parentheses by adding a backslash "\" before the parentheses. For example, 1girl, ganyu (genshin impact) should be written as 1girl, ganyu genshinimpactgenshin impactgenshinimpact.

  • It is recommended to write prompts in logical order,

for example: <1girl/1boy/1other/female/male/...>, <character>, <series>, <artist(s)>, <general tags>, <other tags>, <quality tags> where <quality tags> can be placed at the front.

Characters and Artists

  • For artist styles, simply include the artist's name in the prompt without any prefixes, suffixes, or additional modifiers. It should not be "by xxx", "artist: xxx", just "xxx".

  • For characters, use the format "character name + series". In addition to the character name, you should also add a series tag right after the character's trigger word to indicate which work the character is from. For example, for the character "Ganyu" from "Genshin Impact", the prompt should be "ganyu (genshin impact), genshin impact".

Generation Parameters

Sampler: Euler/Euler a Steps: 28-40 CFG Scale: 3.5-5.5 Resolution:

Resolution (Width x Height): 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768 Aspect Ratio: 9:16, 2:3, 3:4, 1:1, 4:3, 3:2, 16:9 Notes: No need to set CLIP skip No need to use any other VAE models

Resolution (Width x Height)

768x1344

832x1216

896x1152

1024x1024

1152x896

1216x832

1344x768

Aspect Ratio

9:16

2:3

3:4

1:1

4:3

3:2

16:9

Notes:

No need to set CLIP skip

No need to use any other VAE models

Result Example

Prompt

masterpiece, best quality, good quality, nyalia,1girl, animal hands, animal ears, plana (blue archive), heart, halo, pov hands, black eyes, paw gloves, cat ears, pov, gloves, black hairband, long hair, cheek squash, hand on another's face, red halo, cat paws, hand on another's cheek, black choker, fur trim, hairband, symbol-shaped pupils, one eye closed, colored inner hair, braid, hair over one eye, multicolored hair, choker, looking at viewer, single braid, solo focus, pink hair, white background, white hair, fake animal ears, simple background, heart-shaped pupils, blush, red pupils, 1boy, upper body, closed mouth, bare shoulders, pink pupils, pink halo, tail, cheek press, cat tail, off shoulder, black gloves, 1other, two-tone hair, alternate costume, smile, animal ear fluff, sensei (blue archive), black coat, grey hair, long sleeves

Negative Prompt

worst quality, bad quality, mammal, anthro, scalie, lowres, jpeg artifacts, bad anatomy, bad hands, multiple views, signature, watermark, censored, sketch, flat color, pale color, low contrast, muted color, limited palette, greyscale, monochrome, depth of field, sepia, yellow background

Prompt

artist:gomzi,artist:wanke,artist:diyokama,frieren,himmel_(sousou_no_frieren),sousou_no_frieren BREAK,rei_(sanbonzakura),[[artist:fuzichoco]],year 2023,((((alternate_costume)))),solo,1boy,1girl,couple,(lifting person:1.331),(carrying person:1.1),face to face,eye contact,arms around neck,flora background,cowbo shot,

Negative Prompt

lowres,(bad:1.1),error,fewer,extra,mismatched pupils,missing,worst quality,jpeg artifacts,bad quality,watermark,weibo logo,weibo watermark,unfinished,displeasing,chromatic aberration,signature,extra digits,artistic error,username,scan,(abstract:0.909091),artist name,bad anatomy,bad hands,extra fingers,bad feet,wrong foot,wrong hand,bad leg,bad feetfingers,bad proportions,too many hands,too many fingers,text,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,(animal, dool, chibi:1.61051),demon horns,broken horns,single horn,demon wings,extra horns,red skin,tentacle hair

Prompt

1girl,,camellya (wuthering waves),,::, (by kana616:0.8), [(by hen-tie:1.3)|(by kagami_(galgamesion):1.2)], (by kinokohime:1.2), (by yatsuha_(hachiyoh):0.8), year 2024,,parted lips, looking at animal, upper body, profile, holding, centauroid, holding bouquet,,streaked hair, hair flower, multicolored hair, breasts, hair ornament, hair between eyes, jewelry, twintails, white hair,,animal ears, deer girl, flower wreath, white bird, off-shoulder shirt, shirt, sleeves past wrists, deer ears, off shoulder, head wreath, long sleeves,,blurry background, depth of field, bokeh, planted sword, red background, planted, red theme, bird, grass, flower, very awa, masterpiece, best quality, newest, highres, absurdres

Negative Prompt

(worst quality, low quality, ugly:1.4), furry, (multiple_views:2), multiple_views, (comic, 4koma, censored, bar_censor, mosaic_censoring), poorly drawn hands,poorly drawn feet,poorly drawn face,out of frame,mutation,mutated,extra limbs,extra legs,extra arms,disfigured,deformed,cross-eye,blurry,(bad art, bad anatomy:1.4),blurred,text,watermark,negative_hand-neg,((( three fingers, four fingers, six fingers, seven fingers, extra fingers, missing fingers, fused fingers, deformed fingers, ugly fingers,deformed hands, bad hands, worst time, worst hands, wrong hands, twisted hands, ugly hands,deformed toes, fused toes, missing toes,wrong feet, deformed feet, ugly feet))),unaestheticXL_cbp62 -neg,NEGATIVE_HANDS,

SeaArt Exclusive Model:

Lora:

✨
WAI-Pluralistic-Noob
AI styles dump (Illustrious/pony/noob)
NoobAI-XL (NAI-XL)