Bo-Kyeong Kim
commited on
Commit
•
f99066d
1
Parent(s):
678b6ae
Update docs/description.md
Browse files- docs/description.md +6 -1
docs/description.md
CHANGED
|
@@ -6,5 +6,10 @@ This demo showcases a lightweight Stable Diffusion model (SDM) for general-purpo
|
|
| 6 |
|
| 7 |
<br/>
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
### Updates
|
| 10 |
-
[May/31/2023] The demo is running on **T4-small** (4 vCPU · 15 GB RAM · 16GB VRAM). It takes 5~10 seconds for the original model to generate a 512×512 image with 25 denoising steps. Our compressed model accelerates inference speed while preserving visually compelling results.
|
|
|
|
| 6 |
|
| 7 |
<br/>
|
| 8 |
|
| 9 |
+
|
| 10 |
+
### Notice
|
| 11 |
+
- This research is accepted to [**ICCV 2023 Demo Track**](https://iccv2023.thecvf.com/) — title: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation.
|
| 12 |
+
- Please be aware that your prompts are logged (_without_ any personally identifiable information).
|
| 13 |
+
|
| 14 |
### Updates
|
| 15 |
+
- [May/31/2023] The demo is running on **T4-small** (4 vCPU · 15 GB RAM · 16GB VRAM). It takes 5~10 seconds for the original model to generate a 512×512 image with 25 denoising steps. Our compressed model accelerates inference speed while preserving visually compelling results.
|