Update docs/description.md

docs/description.md

@@ -7,19 +7,18 @@ This demo showcases a lightweight Stable Diffusion model (SDM) for general-purpo
 
 <br/>
 
-- This research was accepted to [**ICCV 2023 Demo Track**](https://iccv2023.thecvf.com/) & [**ICML 2023 Workshop on Efficient Systems for Foundation Models** (ES-FoMo)](https://es-fomo.com/).
+- This research was accepted to [**ICCV 2023 Demo Track**](https://iccv2023.thecvf.com/demos-111.php) & [**ICML 2023 Workshop on Efficient Systems for Foundation Models** (ES-FoMo)](https://es-fomo.com/).
 - Please be aware that your prompts are logged, _without_ any personally identifiable information.
 - For different images with the same prompt, please change _Random Seed_ in Advanced Settings (because of using the firstly sampled latent code per seed).
 
 <br/>
 
-**Demo Environment**: [Sept/01/2023] Free CPU-basic (2 vCPU · 16 GB RAM) — 7~10 min slow inference (for a 512×512 image with 25 denoising steps)
-<br/>
- - 🙏 Better to use the quickstart code or Hosted inference API in [BK-SDM-Small Model Card](https://huggingface.co/nota-ai/bk-sdm-small).
-
+**Demo Environment**: [Oct/01/2023] NVIDIA T4-small (4 vCPU · 15 GB RAM · 16GB VRAM) — 5~10 sec inference (for a 512×512 image with 25 denoising steps)
 
 <details>
 <summary>Previous Env Setup:</summary>
+[Sept/01/2023] Free CPU-basic (2 vCPU · 16 GB RAM) — 7~10 min slow inference.
+<br/>
 [Aug/01/2023] NVIDIA T4-small (4 vCPU · 15 GB RAM · 16GB VRAM) — 5~10 sec inference.
 <br/>
 [July/31/2023] Free CPU-basic (2 vCPU · 16 GB RAM) — 7~10 min slow inference.