Commit
•
94b4e9d
1
Parent(s):
3a45ac7
add arch-kd fig
Browse files- docs/description.md +2 -1
docs/description.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
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.
|
| 2 |
|
| 3 |
<center>
|
| 4 |
-
<img src="https://huggingface.co/spaces/nota-ai/
|
| 5 |
</center>
|
| 6 |
|
|
|
|
|
|
| 1 |
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.
|
| 2 |
|
| 3 |
<center>
|
| 4 |
+
<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="70%">
|
| 5 |
</center>
|
| 6 |
|
| 7 |
+
<br/><br/>
|