models/WAI-SHUFFLE-NOOB - v-pred-2.0

WAI-SHUFFLE-NOOB - v-pred-2.0

|
9/2/2025
|
12:58:39 AM
| Discussion|
0
A red-skinned demon girl with green twin-tail hair and horns, surprised with hands on her face, sitting in a warmly lit kitchen at sunset with a large plate of food and a Pepsi bottle on the table.
A tearful anime girl with elf ears sitting in a cafe holding a dripping bubble tea cup, sweat and tears on her face, with a sad cartoon inset of another crying character.

Recommended Prompts

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

1girl, masterpiece, best quality, newest, absurdres, highres, very awa

Recommended Negative Prompts

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

low quality, worst quality, normal quality, text, signature, jpeg artifacts, bad anatomy, old, early

Recommended Parameters

samplers

Euler a

steps

28 - 35

cfg

5 - 7

clip skip

2

resolution

1024x1360, 1024x1360

Recommended Hires (High-Resolution) Parameters

upscaler

R-ESRGAN 4x+ Anime6B

upscale

1.2 - 1.5

steps

20

denoising strength

0.15 - 0.2

Tips

Use webUIs that support v-prediction such as ComfyUI, reForge, Forge, and AUTOMATIC1111 dev branch.

Use Hires.fix instead of ADetailer in most situations.

Style and character reference is NOOB.

Creator Sponsors

If you want to use more my checkpoint online generation, please visit here.

https://tensor.art/u/762555264535746522

If you want to use more my checkpoint online generation, please visit here.

https://tensor.art/u/762555264535746522


V-pred-02

The stability of the limbs, with the overall color leaning towards a warmer tone.

v-prediction versions are experimental models.

You need to use the webui that support v-prediction.

  • ComfyUI

  • reForge

  • Forge

  • AUTOMATIC1111 (dev branch)

  • Use Hires. fix (The situations where ADetailer is needed are not many)

  • Style and Character reference NOOB

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.

Steps: 30

CFG scale: 5-7

Sampler: Euler a

Positive Prompt

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

Negative Prompt

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


V-pred-01

BASE:NOOB V-pred 1.0

This is a test model, attempting to use some unconventional methods to achieve merging.

The merging materials used are not purely from the v-prediction model, so there may be issues that I'm unaware of. If there are any, please leave me a message.

v-prediction versions are experimental models.

You need to use the webui that support v-prediction.

  • ComfyUI

  • reForge

  • Forge

  • AUTOMATIC1111 (dev branch)

  • Use Hires. fix (The situations where ADetailer is needed are not many)

  • Style and Character reference NOOB

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.

Steps: 30

CFG scale: 7

Sampler: Euler a

Positive Prompt

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

Negative Prompt

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


V2

BASE:NOOB eps 1.1

Try to ensure image quality without using quality keywords, in order to create a model that can be easily used by beginners.

  • Not very necessary to use Positive and Negative quality Prompt

  • Use Hires. fix (The situations where ADetailer is needed are not many)

  • Style and Character reference NOOB

All example images are generated at 1024x1360,and Hires upscale: 1.5, Hires steps: 20, Hires upscaler: R-ESRGAN 4x+ Anime6B,Denoising strength: 0.5.

NO Positive and Negative quality TAG

Steps: 30

CFG scale: 5.5

Sampler: Euler a


v1

Steps: 28-35

CFG scale: 5-7

Sampler: Euler a

Positive Prompt

,masterpiece,best quality,newest,

Negative Prompt

low quality,worst quality,normal quality,text,signature,jpeg artifacts,bad anatomy,old,early,copyright name,watermark,artist name,signature,
Previous
Hesperides [Illustrious-V1.0/2.0] - v1.0
Next
Apocalyptic Landscapes by Dever [SDXL] - v1.0

Model Details

Model type

Checkpoint

Base model

NoobAI

Model version

v-pred-2.0

Model hash

cb576b9fc5

Creator

Discussion

Please log in to leave a comment.

Images by WAI-SHUFFLE-NOOB - v-pred-2.0

base model Images