models/Better than words - v2.0

Better than words - v2.0

|
10/23/2023
|
12:24:17 PM
| Comments

Recommended Negative Prompts

(featureless,low-res,low-poly,deformed,worst quality,obese,fat,smooth cartoon,ugly,distortion,flat blah randomness:1.2)

Recommended Parameters

samplers

DPM++ 2M, dpmpp_3m_sde

steps

50 - 64

cfg

7 - 8

Tips

Use 'bad loras' with negative strength to enhance goodness.

Version Highlights

Improvements:

  • Even better NSFW

  • Even better human anatomy

  • More stable, at least for portraits

  • Better image quality

  • No more plastic look which often happened with long prompts

After days of concentrated effort and several setbacks, I finally noticed substantial improvements. I made an entirely new merge, merged it with v1.5, added loras, and stabilized it by merging it once again with v1.5.

This version would be labeled as v3.2 if I uploaded all the versions in between 😎

Creator Sponsors

This is a merge of some of the best (in my opinion) models on Civitai, with some loras, and a touch of magic. 🪄😏

Some of the images were generated with 1 clip skip

Recommended settings:

  • Sampler: DPM++ 2M SDE or 3M SDE or 2M with Karras or Exponential

  • CFG: 5 - 8

  • Steps: 30+

Some of the checkpoints I merged:

  • AlbedoBase XL

  • ⋅ ⊣ Realities Edge XL ⊢ ⋅

  • Realistic Freedom - SFW and NSFW

  • Explicit Freedom - NSFW Waifu

  • Colossus Project XL

  • WoW_XL

Some of the loras I merged:

  • LUT Diffusion XL

  • DetailedEyes_XL

  • NSFW POV All In One SDXL

  • Envy Cute XL 04

  • Perfect Eyes XL

🪄 The final touch of magic is that I used multiple "bad loras" with negative strength to push the model toward greater "goodness".

Previous
RealCartoon-XL - V4
Next
DevlishPhotoRealism SDXL - SDXL 1.4

Model Details

Model type

Checkpoint

Base model

SDXL 1.0

Model version

v2.0

Model hash

620a5cd2ff