Merge branch 'main' into test-sana-lora-training

Author: sayakpaul

examples/dreambooth/README_sana.md

@@ -73,7 +73,7 @@ This will also allow us to push the trained LoRA parameters to the Hugging Face
 Now, we can launch training using:
 
 ```bash
-export MODEL_NAME="Efficient-Large-Model/Sana_1600M_1024px_diffusers"
+export MODEL_NAME="Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers"
 export INSTANCE_DIR="dog"
 export OUTPUT_DIR="trained-sana-lora"
 
@@ -124,4 +124,4 @@ We provide several options for optimizing memory optimization:
 * `cache_latents`: When enabled, we will pre-compute the latents from the input images with the VAE and remove the VAE from memory once done.
 * `--use_8bit_adam`: When enabled, we will use the 8bit version of AdamW provided by the `bitsandbytes` library.
 
-Refer to the [official documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana) of the `SanaPipeline` to know more about the models available under the SANA family and their preferred dtypes during inference.
+Refer to the [official documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana) of the `SanaPipeline` to know more about the models available under the SANA family and their preferred dtypes during inference.