Instructions to use pratik220704/yi-syllable-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pratik220704/yi-syllable-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pratik220704/yi-syllable-diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,20 @@ An unconditional **DDPM** that generates images of **Yi script syllables**
|
|
| 16 |
(Unicode block `U+A000`–`U+A48C`). Trained on 1,165 glyphs rendered from the
|
| 17 |
`NotoSansYi-Regular` font.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Usage
|
| 20 |
|
| 21 |
```python
|
|
|
|
| 16 |
(Unicode block `U+A000`–`U+A48C`). Trained on 1,165 glyphs rendered from the
|
| 17 |
`NotoSansYi-Regular` font.
|
| 18 |
|
| 19 |
+
<p align="center">
|
| 20 |
+
<img src="diffusion_process.gif" width="200" alt="denoising animation">
|
| 21 |
+
<img src="diffusion_steps.gif" width="200" alt="quality vs inference steps">
|
| 22 |
+
</p>
|
| 23 |
+
|
| 24 |
+
Left: reverse diffusion (noise → glyph). Right: the same glyph sharpening as the
|
| 25 |
+
number of inference steps increases.
|
| 26 |
+
|
| 27 |
+
## Sample output
|
| 28 |
+
|
| 29 |
+

|
| 30 |
+
|
| 31 |
+
Top: real glyphs (font). Bottom: generated by this model.
|
| 32 |
+
|
| 33 |
## Usage
|
| 34 |
|
| 35 |
```python
|