RealVisXL V2.0 – SDXL 1.0 – V2.0 (BakedVAE)

The model is already available on Mage.Space (main sponsor)

RealVisXL [ V1.0 (Hugging Face) ] [ V2.0 (Hugging Face) ]

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 Overall Status:
- Training Images: 1740
- Training Steps: 348k
- Approximate percentage of completion: ~30%

RealVisXL V3.0 Status:
- Training Images: +260
- Training Steps: +52k
- Approximate percentage of completion: ~19%

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++ SDE Karras / or another

Hires Fix Parameters:

Upscaler: 4x-UltraSharp upscaler / or another

Denoising strength: 0.1-0.35

Upscale by: 1.1-2.0

Optional Parameters:

ENSD: 31337

This model is:

8ac18d6c 3ba5 43bb a965 b7aeff47fde0 Stable Diffusion Image Generator for Professionals and Enthusiasts RealVisXL V2.0 - SDXL 1.0 - V2.0 (BakedVAE)

The training took place locally on a single video card and took about 140 hours. Version 2.0 is not the final version, the model will be updated.

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

Leave a Comment

Details
Model TypeCHECKPOINT
Base ModelSDXL 1.0
Model Hash74DDA471CC
Model VersionV2.0 (BakedVAE)
Trained Words
Picture of edward.cui

edward.cui