Exploring pre-trained diffusion models in a tuning-free manner
Diffusion models, which utilize a multi-step denoising sampling procedure and leverage extensive image-text pair datasets for training, have emerged as an innovative option among deep generative models. These models exhibit superior performance across various applications, including image synthes...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Thesis-Master by Research |
| 語言: | English |
| 出版: |
Nanyang Technological University
2025
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/181937 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Diffusion models, which utilize a multi-step denoising sampling procedure and
leverage extensive image-text pair datasets for training, have emerged as an innovative
option among deep generative models. These models exhibit superior
performance across various applications, including image synthesis and video generation.
In this thesis, we further explore applications of pre-trained diffusion
models other than text-to-image generation applications in a tuning-free manner.
In Chapter 1, we discuss image morphing between two real images via diffusion
models. Our approach, FreeMorph, is based on key insights regarding attention
interpolation and layout similarity in latent noise, which are critical for enhancing
morphing quality.
In Chapter 2, we discuss attention interpolation in diffusion models. This work
introduces a novel training-free technique named Attention Interpolation via
Diffusion (AID). AID has two key contributions: 1) a fused inner/outer interpolated
attention layer to boost image consistency and fidelity; and 2) selection of
interpolation coefficients via a beta distribution to increase smoothness. |
|---|