Update docs/description.md

docs/description.md

@@ -1,5 +1,5 @@
 This demo showcases a lightweight Stable Diffusion model (SDM) for general-purpose text-to-image synthesis. Our model **BK-SDM-Small** achieves **36% reduced** parameters and latency. This model is bulit with (i) removing several residual and attention blocks from the U-Net of SDM-v1.4 and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite very limited training resources, our model can imitate the original SDM by benefiting from transferred knowledge.
-Our compressed model accelerates inference speed while preserving visually compelling results.
+
 <center>
     <img alt="U-Net architectures and KD-based pretraining" img src="https://huggingface.co/spaces/nota-ai/theme/resolve/3bb3eed8b911d0baf306767bb9548bf732052c53/docs/compressed_stable_diffusion/fig_model.png" width="65%">
 </center>
@@ -15,6 +15,7 @@ Our compressed model accelerates inference speed while preserving visually compe
  - For different images with the same prompt, please change _Random Seed_ in Advanced Settings (because of using the firstly sampled latent code per seed).
  - Some demo codes were borrowed from the repo of Stability AI ([stabilityai/stable-diffusion](https://huggingface.co/spaces/stabilityai/stable-diffusion)) and AK ([akhaliq/small-stable-diffusion-v0](https://huggingface.co/spaces/akhaliq/small-stable-diffusion-v0)). Thanks!
 
-### Compute environment for the demo
- - [June/30/2023] **Free CPU-basic** (2 vCPU · 16 GB RAM) — quite slow inference.
- - [May/31/2023] **T4-small** (4 vCPU · 15 GB RAM · 16GB VRAM) — 5~10 sec for the original model to generate a 512×512 image with 25 denoising steps.
+### Demo Environment
+ - Regardless of machine types, our compressed model achieves speedups while preserving visually compelling results.
+ - [June/30/2023] **Free CPU-basic** (2 vCPU · 16 GB RAM) — 7~10 min slow inference of the original SDM.
+ - [May/31/2023] **NVIDIA T4-small** (4 vCPU · 15 GB RAM · 16GB VRAM) — 5~10 sec inference of the original SDM (for a 512×512 image with 25 denoising steps).