---
license: apache-2.0
tags:
- text-to-image
- flux
datasets:
- DucHaiten/pony-art
- jordandavis/fashion_num_people
- mattmdjaga/human_parsing_dataset
- Voxel51/Describable-Textures-Dataset
- twodgirl/vndb
---

# Flux Latent Preview at Half-Size

The decoder provides a preview image; such thing already exists in the wild for the Flux Dev model.

Max supported resolution is between 768 and 1024px.

Retraining the [text encoder](https://huggingface.co/twodgirl/flux-text-encoder-neutered) and the VAE decoder has reduced the checkpoint size by around 10GB. This set the model's capabilities back by two years.

## Disclaimer

Use of this code and the copy of documentation requires citation and attribution to the author via a link to their Hugging Face profile in all resulting work.