Recommended Prompts
film,bokeh,professional,4k,highly detailed
Recommended Negative Prompts
drawing,painting,crayon,sketch,graphite,impressionist,noisy,soft,3d render,deformed,blurry,ugly
Recommended Parameters
samplers | DPM++ 2S a | |
steps | 25 | |
cfg | 5-9 | |
vae | This version includes the VAE to help newcomers with their setup. | |
resolution | 832×1216, 896×1152 |
Recommended Hires (High-Resolution) Parameters
upscaler | ESRGAN_4x | |
upscale | 1.5 | |
steps | 30-60 | |
denoising strength | 0.3-0.35 |
Tips
- For NSFW content, use SDXXXL.
- To fix the weaknesses, the model will continue to be trained.
Version Highlights
Better eyes, even better realistic look
Creator Sponsors
All sponsors are not affiliates of Diffus. Diffus provides an alternative online Stable Diffusion WebUI experience.
You can also add hires_fix_refiner_pass to you quick list setting to have it on top of you Ui
Version 3.0 of the Realism Engine
In this version we improved the skin realism, the eyes. We also improved the male anatomy.
Keep in mind that this is not a NSFW model. For that I recommend SDXXXL.
Introducing Version 2.0 of the Realism Engine
We are excited to announce that Version 2.0 of the Realism Engine is now available, featuring significant enhancements.
This updated model exhibits superior prompt responsiveness and offers markedly improved overall coherence, including more facial expressions, a greater variety of faces, more poses, and improved hands.
Additionally, we have addressed several quirks from the previous version, such as the challenges in generating nighttime scenes and the issue where increasing the CFG Scale enhanced color vividness without proportionally adjusting contrast. While being capable of producing NSFW content it is less likely to produce it without asking.
This version include the VAE to help newcomers with their setup.
Happy Prompting
Good news for the fans of the original Realism Engine
Realism Engine SDXL is here
Version 1.0 is officially out.
Here’s the recommended setting for Auto1111
Sampler: DPM++ 2S a,
CFG scale range: 5-9,
Hires sampler: DPM++ SDE Karras,
Hires upscaler: ESRGAN_4x,
Refiner switch at: 0.9 (ON THE FIRST PASS ONLY)
Look for this in Setting -> Stable Diffusion
While this model hit some of the key goals I was reaching for, it will continue to be trained to fix the weaknesses.
I appreciate all the good feedback from the community.