Add link to Neuron-optimized version
#275
by
badaoui
HF Staff
- opened
README.md
CHANGED
|
@@ -321,4 +321,16 @@ Based on that information, we estimate the following CO2 emissions using the [Ma
|
|
| 321 |
}
|
| 322 |
```
|
| 323 |
|
| 324 |
-
*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 321 |
}
|
| 322 |
```
|
| 323 |
|
| 324 |
+
*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*
|
| 325 |
+
|
| 326 |
+
---
|
| 327 |
+
## 🚀 AWS Neuron Optimized Version Available
|
| 328 |
+
|
| 329 |
+
A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
|
| 330 |
+
|
| 331 |
+
**[badaoui/CompVis-stable-diffusion-v1-4-neuron](https://huggingface.co/badaoui/CompVis-stable-diffusion-v1-4-neuron)**
|
| 332 |
+
|
| 333 |
+
The Neuron-optimized version provides:
|
| 334 |
+
- Pre-compiled artifacts for faster loading
|
| 335 |
+
- Optimized performance on AWS Neuron devices
|
| 336 |
+
- Same model capabilities with improved inference speed
|