update model card
Browse files
README.md
CHANGED
|
@@ -119,6 +119,7 @@ images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images
|
|
| 119 |
```
|
| 120 |
|
| 121 |
**Note**:
|
|
|
|
| 122 |
If you are limited by TPU memory, please make sure to load the `FlaxStableDiffusionPipeline` in `bfloat16` precision instead of the default `float32` precision as done above. You can do so by telling diffusers to load the weights from "bf16" branch.
|
| 123 |
|
| 124 |
```python
|
|
|
|
| 119 |
```
|
| 120 |
|
| 121 |
**Note**:
|
| 122 |
+
|
| 123 |
If you are limited by TPU memory, please make sure to load the `FlaxStableDiffusionPipeline` in `bfloat16` precision instead of the default `float32` precision as done above. You can do so by telling diffusers to load the weights from "bf16" branch.
|
| 124 |
|
| 125 |
```python
|