RealVisXL V40 – V30 BakedVAE

Related Keywords & Tags

Recommended Negative Prompts

worst quality,low quality,illustration,3d,2d,painting,cartoons,sketch,open mouth
(asymmetry,worst quality,low quality,illustration,3d,2d,painting,cartoons,sketch),open mouth

Recommended Parameters

samplers DPM++ SDE Karras, DPM++ SDE, DPM++ 2M Karras
steps 15-30+
cfg 1-2.5
vae sdxl_vae.safetensors
resolution 896×1152, 1344×768

Recommended Hires (High-Resolution) Parameters

upscaler 4x-UltraSharp upscaler
upscale 1.1-1.5
steps 10
denoising strength 0.1-0.5

Tips

  • Pay attention to the model file name, the part of the name after the underscore is the true version of the model.
  • The model is still in the training phase and may contain artifacts and perform poorly in some cases.
  • Huge thanks to the creators of these great models that were used in the merge.

Version Highlights

  • improved overall model quality

  • increased detail

  • the number of artifacts and mutations has been reduced

  • face quality has been improved

  • (possibly) improved hand quality

Creator Sponsors

All sponsors are not affiliates of Diffus. Diffus provides an alternative online Stable Diffusion WebUI experience.

The model is already available on Mage.Space (main sponsor)
You can also support me directly onBoosty

Use Turbo models with DPM++ SDE Karras sampler, 4-10 steps and CFG Scale 1-2.5

Use Lightning models with DPM++ SDE Karras / DPM++ SDE sampler, 4-6 steps and CFG Scale 1-2

Please pay attention to the model file name, the part of the name after the underscore is the true version of the model.

RealVisXL Hugging Face Full Collection

It’s important! Read it!
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.

RealVisXL V5.0 Status (Updated: Jun 03, 2024):
- Training Images: +420 (V4.0: 3340)
- Training Steps: +84k (V4.0: 672k)
- Approximate percentage of completion: ~10%
- Training Time: ~12.6h (V1.0 - V3.0: ~202h)

The model is aimed at photorealism. Can produce sfw and nsfw images of decent quality.

Recommended Negative Prompt:

(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth

or another negative prompt

Recommended Generation Parameters:
Sampling Steps: 15-30+
Sampling Method: DPM++ 2M Karras / or another

Hires Fix Parameters:

Upscaler: 4x-UltraSharp upscaler / or another

Denoising strength: 0.1-0.5

Upscale by: 1.1-1.5

Optional Parameters:

ENSD: 31337

This model is:

8ac18d6c 3ba5 43bb a965 b7aeff47fde0 Stable Diffusion Image Generator for Professionals and Enthusiasts RealVisXL V40 - V30 BakedVAE

Huge thanks to the creators of these great models that were used in the merge.

DreamShaper XL1.0 by Lykon

Juggernaut XL by KandooAI

SDVN6-RealXL by StableDiffusionVN

TalmendoXL – SDXL Uncensored Full Model by talmendo

WyvernMix (1.5 & XL) by wier

Crystal Clear XL by WarAnakin

ProtoVision XL and DynaVision XL by socalguitarist

Cinemax Alpha | SDXL | Cinema | Filmic | NSFW by viakole

Imperfect portrait by MakeThemComeAliveAIArt

Jib Mix Realistic XL by J1B

LEOSAM’s HelloWorld XL by LEOSAM

Leave a Comment

Models in the Same Collection

An underwater fantasy scene with detailed coral reefs, fish, and an armored warrior holding a spear and sword. Stable Diffusion AI image.

RealVisXL V40 - V30 BakedVAE

Model details

Model TypeCheckpoint
Base ModelSDXL 1.0
Model Hash364cecf630
Model VersionV30 BakedVAE
Trained Words
Creator
SG_161222's Avatar
SG_161222
ReferenceCivitai

Share to

Model Review

Contributor

Picture of Kate Thompson

Kate Thompson

Images by the Same Model