Daniel Regado commited on
Commit ·
5302807
1
Parent(s): b9319f6
Typo fix
Browse files
README.md
CHANGED
|
@@ -79,7 +79,7 @@ image = pipe(
|
|
| 79 |
image.save("result.jpg")
|
| 80 |
```
|
| 81 |
|
| 82 |
-
# GPU Memory
|
| 83 |
|
| 84 |
If you run out of GPU memory, you can use sequential CPU offloading (should work even with 8GB GPUs, assuming enough system RAM). It comes at the cost of longer inference time, as the parameters are only copied to the GPU strictly when required, but the output is exactly the same as using a larger GPU that fits the entire pipeline in memory. Refer to [Memory Optimisations for SD3](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/stable_diffusion_3#memory-optimisations-for-sd3) for additional methods on how to reduce GPU memory usage, such as removing or using a quantized version of the T5-XXL text encoder.
|
| 85 |
|
|
|
|
| 79 |
image.save("result.jpg")
|
| 80 |
```
|
| 81 |
|
| 82 |
+
# GPU Memory Constraints
|
| 83 |
|
| 84 |
If you run out of GPU memory, you can use sequential CPU offloading (should work even with 8GB GPUs, assuming enough system RAM). It comes at the cost of longer inference time, as the parameters are only copied to the GPU strictly when required, but the output is exactly the same as using a larger GPU that fits the entire pipeline in memory. Refer to [Memory Optimisations for SD3](https://huggingface.co/docs/diffusers/en/api/pipelines/stable_diffusion/stable_diffusion_3#memory-optimisations-for-sd3) for additional methods on how to reduce GPU memory usage, such as removing or using a quantized version of the T5-XXL text encoder.
|
| 85 |
|