SDXL-ProteusSigma Training with ZTSNR and NovelAI V3 Improvements
-
10k dataset proof of concept (completed)
-
500k+ dataset finetune (completed) [Note: not aesthetically tuned whatsoever]
-
12M million dataset finetune (planned)
Example Outputs
Combined Proteus and Mobius datasets with ZTSNR and NovelAI V3 Improvements
CUSTOM INFERENCE IS REQUIRED FOR BEST RESULTS!
https://github.com/DataCTE/SDXL-Training-Improvements/tree/main/Comfyui-zsnrnode
use this comfyui custom node from the training repo.
and the workflow here: https://github.com/DataCTE/SDXL-Training-Improvements/blob/main/Comfyui-zsnrnode/ztsnr%2Bv-pred.json
Model Details
- Model Type: SDXL Fine-tuned with ZTSNR and NovelAI V3 Improvements
- Base Model: stabilityai/stable-diffusion-xl-base-1.0
- Training Dataset: 500,000 high-quality images
- License: Apache 2.0
Key Features
- Zero Terminal SNR (ZTSNR) implementation
- Increased σ_max ≈ 20000.0 (NovelAI research)
- High-resolution coherence enhancements
Training Details
Training Configuration
- Learning Rate: 4e-7
- Batch Size: 8
- Gradient Accumulation Steps: 8
- Epochs: 80
- Optimizer: AdamW
- Precision: bfloat16
Repository and Resources
- GitHub Repository: SDXL-Training-Improvements
- Training Code: Available in the repository
- Documentation: Implementation Details
- Issues and Support: GitHub Issues
Citation
@article{ossa2024improvements,
title={Improvements to SDXL in NovelAI Diffusion V3},
author={Ossa, Juan and Doğan, Eren and Birch, Alex and Johnson, F.},
journal={arXiv preprint arXiv:2409.15997v2},
year={2024}
}