|
--- |
|
license: openrail++ |
|
language: |
|
- en |
|
pipeline_tag: text-to-image |
|
tags: |
|
- art |
|
- stable-diffusion-xl |
|
- onnxruntime-directml |
|
library_name: diffusers |
|
--- |
|
Model playground-v2-1024px-aesthetic optimized using Microsoft Olive (https://github.com/microsoft/Olive). Provides massively increased generation speed on my AMD RX 7900 XT on Windows 11 for images of size 1024*1024. (~10s/it --> ~3.80it/s) |
|
|
|
Warning: Requires ONNX Runtime, so this will not work interchangably with any other custom model. |
|
Warning 2: Outputs from this model will contain some noise and may need to be refined using another model. |
|
|
|
Credit for the original model to PlaygroundAI: https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic |
|
|
|
Other models I've uploaded: https://huggingface.co/greentree/SDXL-olive-optimized, https://huggingface.co/greentree/SDXL-Refiner-olive-optimized, https://huggingface.co/greentree/Dreamshaper-XL-olive-optimized |
|
|
|
Also see a collection of many more models like this by https://huggingface.co/softwareweaver |
