---
license: creativeml-openrail-m
---
<b>Please read this!</b><br>
This is not yet the full version of the model (read the <b>"Model Description"</b> section).<br>
For version 6.0 it is recommended to use with VAE (to improve generation quality and get rid of artifacts): https://huggingface.co./stabilityai/sd-vae-ft-mse-original<br>

<b>Model Description</b><br>
Realistic Vision V6.0 "New Vision" is a global update for the Realistic Vision model, which will be released gradually in several beta versions until the full release.<br>

<b>Resolutions</b><br>
- Face Portrait: 896x896<br>
- Portrait: 896x896, 768x1024<br>
- Half Body: 768x1024, 640x1152<br>
- Full Body: 896x896, 768x1024, 640x1152, 1024x768, 1152x640<br>

<b>Improvements</b>
- increased generation resolution to such resolutions as: 896x896, 768x1024, 640x1152, 1024x768, 1152x640. (note. in some cases there may still be mutations, duplications, etc -> will be fixed in future versions).<br>
- improved sfw and nsfw for female and female anatomy (note. not all poses work correctly in such large resolutions -> will be fixed in future versions).<br>

<b>Recommended Workflow</b><br>
Images can be generated with or without Hires.Fix, but it will help improve the generation quality significantly. In some cases it is strictly recommended to use Hires.Fix, namely when generating full body and half body images (note: you can also use Face Fix or ADetailer). Hires.Fix Denoising Strength parameter for each type of images is given below.<br>