Update README.md
Browse files
README.md
CHANGED
|
@@ -13,5 +13,10 @@ As discussed in this blog https://medium.com/@zhiwangshi28/why-flux-lora-so-hard
|
|
| 13 |
The LoRA trained on Flux-Dev2pro yields a much better results when being applied on Flux-dev, just like LoRA trained on SDXL and being applied to SDXL-turbo/lightning.
|
| 14 |
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
|
|
|
|
|
|
|
| 17 |
|
|
|
|
| 13 |
The LoRA trained on Flux-Dev2pro yields a much better results when being applied on Flux-dev, just like LoRA trained on SDXL and being applied to SDXL-turbo/lightning.
|
| 14 |
|
| 15 |
|
| 16 |
+
To use this model, run:
|
| 17 |
+
```
|
| 18 |
+
from diffusers import FluxTransformer2DModel
|
| 19 |
|
| 20 |
+
transformer = FluxTransformer2DModel.from_pretrained("ashen0209/Flux-Dev2Pro", torch_dtype=torch.bfloat16)
|
| 21 |
+
```
|
| 22 |
|