Search Results for author:
Found 1 papers, 0 papers with code
KOALA: Self-Attention Matters in Knowledge Distillation of Latent Diffusion Models for Memory-Efficient and Fast Image Synthesis
We hope that due to its balanced speed-performance tradeoff, our KOALA models can serve as a cost-effective alternative to SDXL in resource-constrained environments.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
