DiffuseHigh for 2K+ resolution with any model
Open
Feature
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
### Feature Idea
"DiffuseHigh enables the pre-trained text-to-image diffusion models (SDXL in this figure) to generate higher-resolution images than the originally trained resolution, e.g., 4×, 16×, without any training or fine-tuning."
https://yhyun225.github.io/DiffuseHigh
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.