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: +0 - Training Steps: +0k - Approximate percentage of completion: ~0%

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

ᅠ

Recommended Negative Prompt:
(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
or another negative prompt

ᅠ

Recommended Generation Parameters:
Sampling Steps: 15-30
Sampling Method: DPM++ SDE Karras

ᅠ

Hires Fix Parameters: 雇用修复参数：

Upscaler: 4x-UltraSharp upscaler

Denoising strength: 0.1-0.35

Upscale by: 1.1-2.0

ᅠ

Optional Parameters:

ENSD: 31337

ᅠ

This model is:

A + B = RealVisXL

A = Trained model on almost 1 thousand images

B = An merge of several models (listed below)

The training took place locally on a single video card and took about 80 hours. Version 1.0 is not the final version, the model will be updated.

ᅠ

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