|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- not-for-all-audiences |
|
pipeline_tag: text-to-image |
|
--- |
|
|
|
<div style="max-width: 500px; margin: 0 auto 0 auto;"> |
|
|
|
 |
|
|
|
</div> |
|
|
|
# **NEW**: FluffyRock Unbound v1.1 is released, with significant improvements! Grab it at https://huggingface.co/RedRocket/Fluffyrock-Unbound/ |
|
|
|
## FluffyRock Unleashed v1.0 |
|
|
|
A finetune of lodestones/fluffyrock-1088-minsnr-zsnr-vpred-ema-pytorch with the following changes: |
|
|
|
- Caption dropout of 10% to improve classifier-free guidance |
|
- Timesteps weighted by 1/(snr+1) to improve output quality |
|
- A higher virtual batch size of 64 |
|
- Includes RedRocket/furception_vae for convenience (licensed separately, please refer to its repository for more information) |
|
|
|
Like its predecessor, this is a v-prediction, zero terminal SNR model. Please use the provided .yaml file (or do whatever your preferred frontend requires you to do to load a model as v-prediction and zero terminal SNR) so the model can load correctly, or you will have a lot of trouble generating correct outputs! |
|
|
|
**NEW Feb 11 2024**: Fluffyrock Unleashed Refiner has been released. Use it as a refiner model for the last 20% of generations for better fine details at no additional compute cost. For best results, use the default noise schedule. |
|
|
|
The VAE decoder is licensed under Furception's license (as of writing CC-BY-NC-SA 4.0 though due to change). All other model components are licensed under the original terms of SD 1.5 (CreativeML OpenRAIL-M). |
|
|
|
Special thanks to @RedHotTensors for general assistance. |
