---
license: mit
library_name: diffusers
pipeline_tag: text-to-image
---

# Mann-E Dreams

<p align="center">
  <img src="./sample-16.png" width=512 height=512 />
</p>

## Description

This is the newest SDXL based model from [Mann-E](https://mann-e.com) platform, which is a generative AI startup based in Iran. This model used thousands of midjourney generated images in order to make it possible to make high-quality images. Also, we've used a lot of tricks in order to make it possible to make the model as fast as SDXL Turbo or any other model which claims to be fast. 

The model has been mostly developed by Founder and CEO of Mann-E, [Muhammadreza Haghiri](https://haghiri75.com/en) and his team. We spent months on collecting the data, labeling them and training this model. The model is _mostly uncensored_ and tested with Automatic1111. 

## Model Settings

- CLIP Skip: 1 or 2 are both fine. 1 gives better results.
- Steps: 4-16. Usually 6 ~ 8 is perfect.
- CFG Scale: 3-5.
- Scale: Unlike our old model, this version supports images up to 1280x1280! Although we recommend 1024x1024 for HD Square images. 
- Sampler : DPM++ SDE Karras


## Additional Notes

- SDXL 1.0 LoRas are working just fine with the model.
- ControlNet, IPAdapter, InstantID are just fine. 

## Donations

- __Tron/USDT (TRC20)__ : `TPXpiWACUZXtUszDbpLeDYR75NQTwngD8o`
- __ETH (ERC20)__: `0x44e262f121b88bcb21caac3d353edd78c3717e08`

## Special Thanks

Special thanks to [RunPod](https://runpod.io) for making the training of the model possible.