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.
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
ᅠ
This model is:
ᅠ
Huge thanks to the creators of these great models that were used in the merge.
SDVN6-RealXL by StableDiffusionVN
TalmendoXL – SDXL Uncensored Full Model by talmendo
ProtoVision XL and DynaVision XL by socalguitarist
Cinemax Alpha | SDXL | Cinema | Filmic | NSFW by viakole