https://github.com/kimrass/ddim
PyTorch implementation of 'DDIM' (Jiaming Song et al., 2020).
https://github.com/kimrass/ddim
celeba ddim pytorch
Last synced: 3 months ago
JSON representation
PyTorch implementation of 'DDIM' (Jiaming Song et al., 2020).
- Host: GitHub
- URL: https://github.com/kimrass/ddim
- Owner: KimRass
- Created: 2024-02-19T09:37:54.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-20T13:12:39.000Z (about 1 year ago)
- Last Synced: 2024-03-20T14:31:22.124Z (about 1 year ago)
- Topics: celeba, ddim, pytorch
- Language: Python
- Homepage:
- Size: 23.8 MB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 1. Sampling
## 1) "normal" Mode
| `mode="normal"`, `trunc_normal_thresh=None` |
|:-:|
| 
|
## 2) "interpolation" Mode
| `mode="interpolation"` |
|:-:|
| 
|
| 
|
| 
|
| 
|
## 3) "grid_interpolation" Mode
| `mode="grid_interpolation"` |
|:-:|
| 
|
| 
|
# 2. Experiments
## 1) Truncated Normal
| `mode="normal"`, `trunc_normal_thresh=0.1` | `mode="normal"`, `trunc_normal_thresh=0.5` |
|:-:|:-:|
| 
| 
|
| `mode="normal"`, `trunc_normal_thresh=1` | `mode="normal"`, `trunc_normal_thresh=1.5` |
|:-:|:-:|
| 
| 
|
| `mode="normal"`, `trunc_normal_thresh=2` | `mode="normal"`, `trunc_normal_thresh=2.5` |
|:-:|:-:|
| 
| 
|
| `mode="normal"`, `trunc_normal_thresh=3` |
|:-:|
| 
|
# 3. Theoretical Background
- "Predicted $x_{0}$":
$$\frac{x_{t} - \sqrt{1 - \alpha_{t}}\epsilon_{\theta}^{(t)}(x_{t})}{\sqrt{\alpha_{t}}}$$
- "Direction pointing to $x_{t}$":
$$\sqrt{1 - \alpha_{t - 1} - \sigma_{t}^{2}} \epsilon_{\theta}^{(t)}(x_{t})$$
## 1) Backward (Denoising) Process
$$x_{t - 1} = \sqrt{\alpha_{t - 1}}\Bigg(\frac{x_{t} - \sqrt{1 - \alpha_{t}}\epsilon_{\theta}}{\sqrt{\alpha_{t}}}\Bigg) + \sqrt{1 - \alpha_{t - 1}}\epsilon_{\theta}$$