up

docs/source/en/api/pipelines/flux2.md

@@ -19,7 +19,7 @@ specific language governing permissions and limitations under the License.
 
 Flux.2 is the recent series of image generation models from Black Forest Labs, preceded by the [Flux.1](./flux.md) series. It is an entirely new model with a new architecture and pre-training done from scratch!
 
-Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux2-dev).
+Original model checkpoints for Flux can be found [here](https://huggingface.co/black-forest-labs). Original inference code can be found [here](https://github.com/black-forest-labs/flux2).
 
 > [!TIP]
 > Flux2 can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out [this section](https://huggingface.co/blog/sd3#memory-optimizations-for-sd3) for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to [this blog post](https://huggingface.co/blog/quanto-diffusers) to learn more.

examples/dreambooth/README_flux2.md

@@ -2,7 +2,7 @@
 
 [DreamBooth](https://huggingface.co/papers/2208.12242) is a method to personalize image generation models given just a few (3~5) images of a subject/concept.
 
-The `train_dreambooth_lora_flux2.py` script shows how to implement the training procedure for [LoRAs](https://huggingface.co/blog/lora) and adapt it for [FLUX.2 [dev]](https://github.com/black-forest-labs/flux2-dev).
+The `train_dreambooth_lora_flux2.py` script shows how to implement the training procedure for [LoRAs](https://huggingface.co/blog/lora) and adapt it for [FLUX.2 [dev]](https://github.com/black-forest-labs/flux2).
 
 > [!NOTE]
 > **Memory consumption**