[docs] Remove Flax (#12244)

* remove flax

* toctree

* feedback

README.md

@@ -37,7 +37,7 @@ limitations under the License.
 
 ## Installation
 
-We recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https://pytorch.org/get-started/locally/) and [Flax](https://flax.readthedocs.io/en/latest/#installation), please refer to their official documentation.
+We recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https://pytorch.org/get-started/locally/), please refer to their official documentation.
 
 ### PyTorch
 
@@ -53,14 +53,6 @@ With `conda` (maintained by the community):
 conda install -c conda-forge diffusers
 ```
 
-### Flax
-
-With `pip` (official package):
-
-```bash
-pip install --upgrade diffusers[flax]
-```
-
 ### Apple Silicon (M1/M2) support
 
 Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggingface.co/docs/diffusers/optimization/mps) guide.

docs/source/en/_toctree.yml

@@ -194,8 +194,6 @@
 - title: Model accelerators and hardware
   isExpanded: false
   sections:
-  - local: using-diffusers/stable_diffusion_jax_how_to
-    title: JAX/Flax
   - local: optimization/onnx
     title: ONNX
   - local: optimization/open_vino

docs/source/en/api/models/autoencoderkl.md

@@ -44,15 +44,3 @@ model = AutoencoderKL.from_single_file(url)
 ## DecoderOutput
 
 [[autodoc]] models.autoencoders.vae.DecoderOutput
-
-## FlaxAutoencoderKL
-
-[[autodoc]] FlaxAutoencoderKL
-
-## FlaxAutoencoderKLOutput
-
-[[autodoc]] models.vae_flax.FlaxAutoencoderKLOutput
-
-## FlaxDecoderOutput
-
-[[autodoc]] models.vae_flax.FlaxDecoderOutput

docs/source/en/api/models/controlnet.md

@@ -40,11 +40,3 @@ pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=contro
 ## ControlNetOutput
 
 [[autodoc]] models.controlnets.controlnet.ControlNetOutput
-
-## FlaxControlNetModel
-
-[[autodoc]] FlaxControlNetModel
-
-## FlaxControlNetOutput
-
-[[autodoc]] models.controlnets.controlnet_flax.FlaxControlNetOutput

docs/source/en/api/models/overview.md

@@ -19,10 +19,6 @@ All models are built from the base [`ModelMixin`] class which is a [`torch.nn.Mo
 ## ModelMixin
 [[autodoc]] ModelMixin
 
-## FlaxModelMixin
-
-[[autodoc]] FlaxModelMixin
-
 ## PushToHubMixin
 
 [[autodoc]] utils.PushToHubMixin

docs/source/en/api/models/unet2d-cond.md

@@ -23,9 +23,3 @@ The abstract from the paper is:
 
 ## UNet2DConditionOutput
 [[autodoc]] models.unets.unet_2d_condition.UNet2DConditionOutput
-
-## FlaxUNet2DConditionModel
-[[autodoc]] models.unets.unet_2d_condition_flax.FlaxUNet2DConditionModel
-
-## FlaxUNet2DConditionOutput
-[[autodoc]] models.unets.unet_2d_condition_flax.FlaxUNet2DConditionOutput

docs/source/en/api/outputs.md

@@ -54,10 +54,6 @@ To check a specific pipeline or model output, refer to its corresponding API doc
 
 [[autodoc]] pipelines.ImagePipelineOutput
 
-## FlaxImagePipelineOutput
-
-[[autodoc]] pipelines.pipeline_flax_utils.FlaxImagePipelineOutput
-
 ## AudioPipelineOutput
 
 [[autodoc]] pipelines.AudioPipelineOutput

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

@@ -72,11 +72,3 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 
 ## StableDiffusionPipelineOutput
 [[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
-
-## FlaxStableDiffusionControlNetPipeline
-[[autodoc]] FlaxStableDiffusionControlNetPipeline
-	- all
-	- __call__
-
-## FlaxStableDiffusionControlNetPipelineOutput
-[[autodoc]] pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput

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

@@ -106,10 +106,6 @@ The table below lists all the pipelines currently available in 🤗 Diffusers an
 
 [[autodoc]] pipelines.StableDiffusionMixin.disable_freeu
 
-## FlaxDiffusionPipeline
-
-[[autodoc]] pipelines.pipeline_flax_utils.FlaxDiffusionPipeline
-
 ## PushToHubMixin
 
 [[autodoc]] utils.PushToHubMixin

docs/source/en/api/pipelines/stable_diffusion/img2img.md

@@ -47,13 +47,3 @@ Make sure to check out the Stable Diffusion [Tips](overview#tips) section to lea
 ## StableDiffusionPipelineOutput
 
 [[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
-
-## FlaxStableDiffusionImg2ImgPipeline
-
-[[autodoc]] FlaxStableDiffusionImg2ImgPipeline
-	- all
-	- __call__
-
-## FlaxStableDiffusionPipelineOutput
-
-[[autodoc]] pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput

docs/source/en/api/pipelines/stable_diffusion/inpaint.md

@@ -49,13 +49,3 @@ If you're interested in using one of the official checkpoints for a task, explor
 ## StableDiffusionPipelineOutput
 
 [[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
-
-## FlaxStableDiffusionInpaintPipeline
-
-[[autodoc]] FlaxStableDiffusionInpaintPipeline
-	- all
-	- __call__
-
-## FlaxStableDiffusionPipelineOutput
-
-[[autodoc]] pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput

docs/source/en/api/pipelines/stable_diffusion/text2img.md

@@ -51,13 +51,3 @@ If you're interested in using one of the official checkpoints for a task, explor
 ## StableDiffusionPipelineOutput
 
 [[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
-
-## FlaxStableDiffusionPipeline
-
-[[autodoc]] FlaxStableDiffusionPipeline
-	- all
-	- __call__
-
-## FlaxStableDiffusionPipelineOutput
-
-[[autodoc]] pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput

docs/source/en/installation.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # Installation
 
-Diffusers is tested on Python 3.8+, PyTorch 1.4+, and Flax 0.4.1+. Follow the installation instructions for the deep learning library you're using, [PyTorch](https://pytorch.org/get-started/locally/) or [Flax](https://flax.readthedocs.io/en/latest/).
+Diffusers is tested on Python 3.8+ and PyTorch 1.4+. Install [PyTorch](https://pytorch.org/get-started/locally/) according to your system and setup.
 
 Create a [virtual environment](https://packaging.python.org/guides/installing-using-pip-and-virtual-environments/) for easier management of separate projects and to avoid compatibility issues between dependencies. Use [uv](https://docs.astral.sh/uv/), a Rust-based Python package and project manager, to create a virtual environment and install Diffusers.
 
@@ -32,12 +32,6 @@ PyTorch only supports Python 3.8 - 3.11 on Windows.
 uv pip install diffusers["torch"] transformers
 ```
 
-Use the command below for Flax.
-
-```bash
-uv pip install diffusers["flax"] transformers
-```
-
 </hfoption>
 <hfoption id="conda">
 
@@ -71,27 +65,12 @@ An editable install is recommended for development workflows or if you're using
 
 Clone the repository and install Diffusers with the following commands.
 
-<hfoptions id="editable">
-<hfoption id="PyTorch">
-
 ```bash
 git clone https://github.com/huggingface/diffusers.git
 cd diffusers
 uv pip install -e ".[torch]"
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```bash
-git clone https://github.com/huggingface/diffusers.git
-cd diffusers
-uv pip install -e ".[flax]"
-```
-
-</hfoption>
-</hfoptions>
-
 > [!WARNING]
 > You must keep the `diffusers` folder if you want to keep using the library with the editable install.
 
@@ -140,7 +119,7 @@ For more details about managing and cleaning the cache, take a look at the [Unde
 ## Telemetry logging
 
 Diffusers gathers telemetry information during [`~DiffusionPipeline.from_pretrained`] requests.
-The data gathered includes the Diffusers and PyTorch/Flax version, the requested model or pipeline class,
+The data gathered includes the Diffusers and PyTorch version, the requested model or pipeline class,
 and the path to a pretrained checkpoint if it is hosted on the Hub.
 
 This usage data helps us debug issues and prioritize new features.

docs/source/en/training/controlnet.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 [ControlNet](https://hf.co/papers/2302.05543) models are adapters trained on top of another pretrained model. It allows for a greater degree of control over image generation by conditioning the model with an additional input image. The input image can be a canny edge, depth map, human pose, and many more.
 
-If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing`, `gradient_accumulation_steps`, and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers). JAX/Flax training is also supported for efficient training on TPUs and GPUs, but it doesn't support gradient checkpointing or xFormers. You should have a GPU with >30GB of memory if you want to train faster with Flax.
+If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing`, `gradient_accumulation_steps`, and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers).
 
 This guide will explore the [train_controlnet.py](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/train_controlnet.py) training script to help you become familiar with it, and how you can adapt it for your own use-case.
 
@@ -28,45 +28,10 @@ pip install .
 
 Then navigate to the example folder containing the training script and install the required dependencies for the script you're using:
 
-<hfoptions id="installation">
-<hfoption id="PyTorch">
 ```bash
 cd examples/controlnet
 pip install -r requirements.txt
 ```
-</hfoption>
-<hfoption id="Flax">
-
-If you have access to a TPU, the Flax training script runs even faster! Let's run the training script on the [Google Cloud TPU VM](https://cloud.google.com/tpu/docs/run-calculation-jax). Create a single TPU v4-8 VM and connect to it:
-
-```bash
-ZONE=us-central2-b
-TPU_TYPE=v4-8
-VM_NAME=hg_flax
-
-gcloud alpha compute tpus tpu-vm create $VM_NAME \
- --zone $ZONE \
- --accelerator-type $TPU_TYPE \
- --version  tpu-vm-v4-base
-
-gcloud alpha compute tpus tpu-vm ssh $VM_NAME --zone $ZONE -- \
-```
-
-Install JAX 0.4.5:
-
-```bash
-pip install "jax[tpu]==0.4.5" -f https://storage.googleapis.com/jax-releases/libtpu_releases.html
-```
-
-Then install the required dependencies for the Flax script:
-
-```bash
-cd examples/controlnet
-pip install -r requirements_flax.txt
-```
-
-</hfoption>
-</hfoptions>
 
 <Tip>
 
@@ -120,7 +85,7 @@ Many of the basic and important parameters are described in the [Text-to-image](
 
 ### Min-SNR weighting
 
-The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
+The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch.
 
 Add the `--snr_gamma` parameter and set it to the recommended value of 5.0:
 
@@ -272,9 +237,6 @@ That's it! You don't need to add any additional parameters to your training comm
 </hfoption>
 </hfoptions>
 
-<hfoptions id="training-inference">
-<hfoption id="PyTorch">
-
 ```bash
 export MODEL_DIR="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export OUTPUT_DIR="path/to/save/model"
@@ -292,47 +254,6 @@ accelerate launch train_controlnet.py \
  --push_to_hub
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-With Flax, you can [profile your code](https://jax.readthedocs.io/en/latest/profiling.html) by adding the `--profile_steps==5` parameter to your training command. Install the Tensorboard profile plugin:
-
-```bash
-pip install tensorflow tensorboard-plugin-profile
-tensorboard --logdir runs/fill-circle-100steps-20230411_165612/
-```
-
-Then you can inspect the profile at [http://localhost:6006/#profile](http://localhost:6006/#profile).
-
-<Tip warning={true}>
-
-If you run into version conflicts with the plugin, try uninstalling and reinstalling all versions of TensorFlow and Tensorboard. The debugging functionality of the profile plugin is still experimental, and not all views are fully functional. The `trace_viewer` cuts off events after 1M, which can result in all your device traces getting lost if for example, you profile the compilation step by accident.
-
-</Tip>
-
-```bash
-python3 train_controlnet_flax.py \
- --pretrained_model_name_or_path=$MODEL_DIR \
- --output_dir=$OUTPUT_DIR \
- --dataset_name=fusing/fill50k \
- --resolution=512 \
- --learning_rate=1e-5 \
- --validation_image "./conditioning_image_1.png" "./conditioning_image_2.png" \
- --validation_prompt "red circle with blue background" "cyan circle with brown floral background" \
- --validation_steps=1000 \
- --train_batch_size=2 \
- --revision="non-ema" \
- --from_pt \
- --report_to="wandb" \
- --tracker_project_name=$HUB_MODEL_ID \
- --num_train_epochs=11 \
- --push_to_hub \
- --hub_model_id=$HUB_MODEL_ID
-```
-
-</hfoption>
-</hfoptions>
-
 Once training is complete, you can use your newly trained model for inference!
 
 ```py

docs/source/en/training/dreambooth.md

@@ -14,7 +14,7 @@ specific language governing permissions and limitations under the License.
 
 [DreamBooth](https://huggingface.co/papers/2208.12242) is a training technique that updates the entire diffusion model by training on just a few images of a subject or style. It works by associating a special word in the prompt with the example images.
 
-If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing` and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers). JAX/Flax training is also supported for efficient training on TPUs and GPUs, but it doesn't support gradient checkpointing or xFormers. You should have a GPU with >30GB of memory if you want to train faster with Flax.
+If you're training on a GPU with limited vRAM, you should try enabling the `gradient_checkpointing` and `mixed_precision` parameters in the training command. You can also reduce your memory footprint by using memory-efficient attention with [xFormers](../optimization/xformers).
 
 This guide will explore the [train_dreambooth.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py) script to help you become more familiar with it, and how you can adapt it for your own use-case.
 
@@ -28,25 +28,11 @@ pip install .
 
 Navigate to the example folder with the training script and install the required dependencies for the script you're using:
 
-<hfoptions id="installation">
-<hfoption id="PyTorch">
-
 ```bash
 cd examples/dreambooth
 pip install -r requirements.txt
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```bash
-cd examples/dreambooth
-pip install -r requirements_flax.txt
-```
-
-</hfoption>
-</hfoptions>
-
 <Tip>
 
 🤗 Accelerate is a library for helping you train on multiple GPUs/TPUs or with mixed-precision. It'll automatically configure your training setup based on your hardware and environment. Take a look at the 🤗 Accelerate [Quick tour](https://huggingface.co/docs/accelerate/quicktour) to learn more.
@@ -110,7 +96,7 @@ Some basic and important parameters to know and specify are:
 
 ### Min-SNR weighting
 
-The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
+The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch.
 
 Add the `--snr_gamma` parameter and set it to the recommended value of 5.0:
 
@@ -311,9 +297,6 @@ That's it! You don't need to add any additional parameters to your training comm
 </hfoption>
 </hfoptions>
 
-<hfoptions id="training-inference">
-<hfoption id="PyTorch">
-
 ```bash
 export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
 export INSTANCE_DIR="./dog"
@@ -334,29 +317,6 @@ accelerate launch train_dreambooth.py \
   --push_to_hub
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```bash
-export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
-export INSTANCE_DIR="./dog"
-export OUTPUT_DIR="path-to-save-model"
-
-python train_dreambooth_flax.py \
-  --pretrained_model_name_or_path=$MODEL_NAME  \
-  --instance_data_dir=$INSTANCE_DIR \
-  --output_dir=$OUTPUT_DIR \
-  --instance_prompt="a photo of sks dog" \
-  --resolution=512 \
-  --train_batch_size=1 \
-  --learning_rate=5e-6 \
-  --max_train_steps=400 \
-  --push_to_hub
-```
-
-</hfoption>
-</hfoptions>
-
 Once training is complete, you can use your newly trained model for inference!
 
 <Tip>
@@ -383,9 +343,6 @@ image.save("dog-bucket.png")
 
 </Tip>
 
-<hfoptions id="training-inference">
-<hfoption id="PyTorch">
-
 ```py
 from diffusers import DiffusionPipeline
 import torch
@@ -395,39 +352,6 @@ image = pipeline("A photo of sks dog in a bucket", num_inference_steps=50, guida
 image.save("dog-bucket.png")
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```py
-import jax
-import numpy as np
-from flax.jax_utils import replicate
-from flax.training.common_utils import shard
-from diffusers import FlaxStableDiffusionPipeline
-
-pipeline, params = FlaxStableDiffusionPipeline.from_pretrained("path-to-your-trained-model", dtype=jax.numpy.bfloat16)
-
-prompt = "A photo of sks dog in a bucket"
-prng_seed = jax.random.PRNGKey(0)
-num_inference_steps = 50
-
-num_samples = jax.device_count()
-prompt = num_samples * [prompt]
-prompt_ids = pipeline.prepare_inputs(prompt)
-
-# shard inputs and rng
-params = replicate(params)
-prng_seed = jax.random.split(prng_seed, jax.device_count())
-prompt_ids = shard(prompt_ids)
-
-images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
-images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
-image.save("dog-bucket.png")
-```
-
-</hfoption>
-</hfoptions>
-
 ## LoRA
 
 LoRA is a training technique for significantly reducing the number of trainable parameters. As a result, training is faster and it is easier to store the resulting weights because they are a lot smaller (~100MBs). Use the [train_dreambooth_lora.py](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py) script to train with LoRA.

docs/source/en/training/kandinsky.md

@@ -88,7 +88,7 @@ Most of the parameters are identical to the parameters in the [Text-to-image](te
 
 ### Min-SNR weighting
 
-The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
+The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch.
 
 Add the `--snr_gamma` parameter and set it to the recommended value of 5.0:
 

docs/source/en/training/lora.md

@@ -38,25 +38,11 @@ pip install .
 
 Navigate to the example folder with the training script and install the required dependencies for the script you're using:
 
-<hfoptions id="installation">
-<hfoption id="PyTorch">
-
 ```bash
 cd examples/text_to_image
 pip install -r requirements.txt
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```bash
-cd examples/text_to_image
-pip install -r requirements_flax.txt
-```
-
-</hfoption>
-</hfoptions>
-
 <Tip>
 
 🤗 Accelerate is a library for helping you train on multiple GPUs/TPUs or with mixed-precision. It'll automatically configure your training setup based on your hardware and environment. Take a look at the 🤗 Accelerate [Quick tour](https://huggingface.co/docs/accelerate/quicktour) to learn more.

docs/source/en/training/overview.md

@@ -23,18 +23,18 @@ Each training script is:
 
 Our current collection of training scripts include:
 
-| Training | SDXL-support | LoRA-support | Flax-support |
-|---|---|---|---|
-| [unconditional image generation](https://github.com/huggingface/diffusers/tree/main/examples/unconditional_image_generation) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) |  |  |  |
-| [text-to-image](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image) | 👍 | 👍 | 👍 |
-| [textual inversion](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb) |  |  | 👍 |
-| [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb) | 👍 | 👍 | 👍 |
-| [ControlNet](https://github.com/huggingface/diffusers/tree/main/examples/controlnet) | 👍 |  | 👍 |
-| [InstructPix2Pix](https://github.com/huggingface/diffusers/tree/main/examples/instruct_pix2pix) | 👍 |  |  |
-| [Custom Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/custom_diffusion) |  |  |  |
-| [T2I-Adapters](https://github.com/huggingface/diffusers/tree/main/examples/t2i_adapter) | 👍 |  |  |
-| [Kandinsky 2.2](https://github.com/huggingface/diffusers/tree/main/examples/kandinsky2_2/text_to_image) |  | 👍 |  |
-| [Wuerstchen](https://github.com/huggingface/diffusers/tree/main/examples/wuerstchen/text_to_image) |  | 👍 |  |
+| Training | SDXL-support | LoRA-support |
+|---|---|---|
+| [unconditional image generation](https://github.com/huggingface/diffusers/tree/main/examples/unconditional_image_generation) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) |  |  |
+| [text-to-image](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image) | 👍 | 👍 |
+| [textual inversion](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb) |  |  |
+| [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb) | 👍 | 👍 |
+| [ControlNet](https://github.com/huggingface/diffusers/tree/main/examples/controlnet) | 👍 |  |
+| [InstructPix2Pix](https://github.com/huggingface/diffusers/tree/main/examples/instruct_pix2pix) | 👍 |  |
+| [Custom Diffusion](https://github.com/huggingface/diffusers/tree/main/examples/custom_diffusion) |  |  |
+| [T2I-Adapters](https://github.com/huggingface/diffusers/tree/main/examples/t2i_adapter) | 👍 |  |
+| [Kandinsky 2.2](https://github.com/huggingface/diffusers/tree/main/examples/kandinsky2_2/text_to_image) |  | 👍 |
+| [Wuerstchen](https://github.com/huggingface/diffusers/tree/main/examples/wuerstchen/text_to_image) |  | 👍 |
 
 These examples are **actively** maintained, so please feel free to open an issue if they aren't working as expected. If you feel like another training example should be included, you're more than welcome to start a [Feature Request](https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&template=feature_request.md&title=) to discuss your feature idea with us and whether it meets our criteria of being self-contained, easy-to-tweak, beginner-friendly, and single-purpose.
 
@@ -48,7 +48,7 @@ cd diffusers
 pip install .
 ```
 
-Then navigate to the folder of the training script (for example, [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth)) and install the `requirements.txt` file. Some training scripts have a specific requirement file for SDXL, LoRA or Flax. If you're using one of these scripts, make sure you install its corresponding requirements file.
+Then navigate to the folder of the training script (for example, [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth)) and install the `requirements.txt` file. Some training scripts have a specific requirement file for SDXL or LoRA. If you're using one of these scripts, make sure you install its corresponding requirements file.
 
 ```bash
 cd examples/dreambooth

docs/source/en/training/sdxl.md

@@ -96,7 +96,7 @@ Most of the parameters are identical to the parameters in the [Text-to-image](te
 
 ### Min-SNR weighting
 
-The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting either `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
+The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting either `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch.
 
 Add the `--snr_gamma` parameter and set it to the recommended value of 5.0:
 

docs/source/en/training/text2image.md

@@ -20,7 +20,7 @@ The text-to-image script is experimental, and it's easy to overfit and run into
 
 Text-to-image models like Stable Diffusion are conditioned to generate images given a text prompt.
 
-Training a model can be taxing on your hardware, but if you enable `gradient_checkpointing` and `mixed_precision`, it is possible to train a model on a single 24GB GPU. If you're training with larger batch sizes or want to train faster, it's better to use GPUs with more than 30GB of memory. You can reduce your memory footprint by enabling memory-efficient attention with [xFormers](../optimization/xformers). JAX/Flax training is also supported for efficient training on TPUs and GPUs, but it doesn't support gradient checkpointing, gradient accumulation or xFormers. A GPU with at least 30GB of memory or a TPU v3 is recommended for training with Flax.
+Training a model can be taxing on your hardware, but if you enable `gradient_checkpointing` and `mixed_precision`, it is possible to train a model on a single 24GB GPU. If you're training with larger batch sizes or want to train faster, it's better to use GPUs with more than 30GB of memory. You can reduce your memory footprint by enabling memory-efficient attention with [xFormers](../optimization/xformers).
 
 This guide will explore the [train_text_to_image.py](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) training script to help you become familiar with it, and how you can adapt it for your own use-case.
 
@@ -34,20 +34,10 @@ pip install .
 
 Then navigate to the example folder containing the training script and install the required dependencies for the script you're using:
 
-<hfoptions id="installation">
-<hfoption id="PyTorch">
 ```bash
 cd examples/text_to_image
 pip install -r requirements.txt
 ```
-</hfoption>
-<hfoption id="Flax">
-```bash
-cd examples/text_to_image
-pip install -r requirements_flax.txt
-```
-</hfoption>
-</hfoptions>
 
 <Tip>
 
@@ -106,7 +96,7 @@ Some basic and important parameters include:
 
 ### Min-SNR weighting
 
-The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch and is unavailable in the Flax training script.
+The [Min-SNR](https://huggingface.co/papers/2303.09556) weighting strategy can help with training by rebalancing the loss to achieve faster convergence. The training script supports predicting `epsilon` (noise) or `v_prediction`, but Min-SNR is compatible with both prediction types. This weighting strategy is only supported by PyTorch.
 
 Add the `--snr_gamma` parameter and set it to the recommended value of 5.0:
 
@@ -155,9 +145,6 @@ Lastly, the [training loop](https://github.com/huggingface/diffusers/blob/8959c5
 
 Once you've made all your changes or you're okay with the default configuration, you're ready to launch the training script! 🚀
 
-<hfoptions id="training-inference">
-<hfoption id="PyTorch">
-
 Let's train on the [Naruto BLIP captions](https://huggingface.co/datasets/lambdalabs/naruto-blip-captions) dataset to generate your own Naruto characters. Set the environment variables `MODEL_NAME` and `dataset_name` to the model and the dataset (either from the Hub or a local path). If you're training on more than one GPU, add the `--multi_gpu` parameter to the `accelerate launch` command.
 
 <Tip>
@@ -187,43 +174,8 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
   --push_to_hub
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-Training with Flax can be faster on TPUs and GPUs thanks to [@duongna211](https://github.com/duongna21). Flax is more efficient on a TPU, but GPU performance is also great.
-
-Set the environment variables `MODEL_NAME` and `dataset_name` to the model and the dataset (either from the Hub or a local path).
-
-<Tip>
-
-To train on a local dataset, set the `TRAIN_DIR` and `OUTPUT_DIR` environment variables to the path of the dataset and where to save the model to.
-
-</Tip>
-
-```bash
-export MODEL_NAME="stable-diffusion-v1-5/stable-diffusion-v1-5"
-export dataset_name="lambdalabs/naruto-blip-captions"
-
-python train_text_to_image_flax.py \
-  --pretrained_model_name_or_path=$MODEL_NAME \
-  --dataset_name=$dataset_name \
-  --resolution=512 --center_crop --random_flip \
-  --train_batch_size=1 \
-  --max_train_steps=15000 \
-  --learning_rate=1e-05 \
-  --max_grad_norm=1 \
-  --output_dir="sd-naruto-model" \
-  --push_to_hub
-```
-
-</hfoption>
-</hfoptions>
-
 Once training is complete, you can use your newly trained model for inference:
 
-<hfoptions id="training-inference">
-<hfoption id="PyTorch">
-
 ```py
 from diffusers import StableDiffusionPipeline
 import torch
@@ -234,39 +186,6 @@ image = pipeline(prompt="yoda").images[0]
 image.save("yoda-naruto.png")
 ```
 
-</hfoption>
-<hfoption id="Flax">
-
-```py
-import jax
-import numpy as np
-from flax.jax_utils import replicate
-from flax.training.common_utils import shard
-from diffusers import FlaxStableDiffusionPipeline
-
-pipeline, params = FlaxStableDiffusionPipeline.from_pretrained("path/to/saved_model", dtype=jax.numpy.bfloat16)
-
-prompt = "yoda naruto"
-prng_seed = jax.random.PRNGKey(0)
-num_inference_steps = 50
-
-num_samples = jax.device_count()
-prompt = num_samples * [prompt]
-prompt_ids = pipeline.prepare_inputs(prompt)
-
-# shard inputs and rng
-params = replicate(params)
-prng_seed = jax.random.split(prng_seed, jax.device_count())
-prompt_ids = shard(prompt_ids)
-
-images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
-images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
-image.save("yoda-naruto.png")
-```
-
-</hfoption>
-</hfoptions>
-
 ## Next steps
 
 Congratulations on training your own text-to-image model! To learn more about how to use your new model, the following guides may be helpful: