### Install Example Script Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/lora.md

Installs the necessary Python packages for a specific example script, such as text-to-image LoRA training. Ensure you are in the correct example directory.

```bash
cd examples/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Install Example-Specific Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/cogvideox.md

Navigates to the specific example directory and installs the required Python dependencies listed in the requirements file.

```bash
cd examples/cogvideo
pip install -r requirements.txt
```

--------------------------------

### Install Wuerstchen Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/zh/training/wuerstchen.md

Navigate to the Wuerstchen text-to-image example directory and install its specific requirements.

```bash
cd examples/wuerstchen/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Install Textual Inversion Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/text_inversion.md

Navigate to the textual inversion example directory and install the necessary Python requirements.

```bash
cd examples/textual_inversion
pip install -r requirements.txt
```

--------------------------------

### Install Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/CONTRIBUTING.md

After cloning, navigate to the repository and install the necessary dependencies for a specific example using its requirements file.

```bash
cd diffusers
pip install -r examples/<your-example-folder>/requirements.txt
```

--------------------------------

### Install SDXL Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/sdxl.md

Navigate to the text-to-image examples directory and install the specific requirements for SDXL training. Ensure you are in the correct directory before running this command.

```bash
cd examples/text_to_image
pip install -r requirements_sdxl.txt
```

--------------------------------

### Install Text-to-Image LoRA Requirements (PyTorch)

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/zh/training/lora.md

Navigate to the text-to-image example directory and install PyTorch-specific requirements for LoRA training.

```bash
cd examples/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Install Training Script Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/lcm_distill.md

Navigate to the consistency distillation example directory and install the necessary dependencies for the training script using requirements.txt.

```bash
cd examples/consistency_distillation
pip install -r requirements.txt
```

--------------------------------

### Setup Development Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion/README.md

Commands to clone the repository, install dependencies, and configure the Accelerate environment for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
pip install -r requirements.txt
pip install clip-retrieval
accelerate config
```

--------------------------------

### Setup Development Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_lumina2.md

Commands to clone the repository, install dependencies, and configure the Accelerate environment for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/dreambooth
pip install -r requirements_sana.txt
accelerate config
```

--------------------------------

### Setup Development Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_z_image.md

Commands to clone the repository, install dependencies, and configure the Accelerate environment for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/dreambooth
pip install -r requirements_z_image.txt
accelerate config
```

--------------------------------

### Install Text-to-Image LoRA Requirements (Flax)

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/zh/training/lora.md

Navigate to the text-to-image example directory and install Flax-specific requirements for LoRA training.

```bash
cd examples/text_to_image
pip install -r requirements_flax.txt
```

--------------------------------

### Setup Development Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sdxl.md

Commands to clone the diffusers repository, install dependencies, and configure the accelerate environment for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/dreambooth
pip install -r requirements_sdxl.txt
accelerate config
```

--------------------------------

### Install Diffusers Library from Source

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/overview.md

Commands to clone the Diffusers repository and install the library in a local environment. This is the recommended setup for running the provided training scripts.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
```

--------------------------------

### Setup Development Environment for ControlNet Training

Source: https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sd3.md

Commands to clone the diffusers repository, install required dependencies, and initialize the Accelerate configuration for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/controlnet
pip install -r requirements_sd3.txt
accelerate config
```

--------------------------------

### Install Kandinsky Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/kandinsky.md

Navigate to the Kandinsky 2.2 text-to-image example directory and install the necessary dependencies for the training scripts.

```bash
cd examples/kandinsky2_2/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Setup Diffusers Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/research_projects/onnxruntime/text_to_image/README.md

Commands to clone the repository, install dependencies, and configure the Accelerate environment for training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/text_to_image
pip install -r requirements.txt
accelerate config
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/research_projects/multi_token_textual_inversion/README.md

Commands to clone the repository, install the library from source, and install example-specific requirements.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/textual_inversion
pip install -r requirements.txt
accelerate config
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/t2i_adapters.md

Commands to clone the repository, install the library from source, and install the specific requirements for T2I-Adapter training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/t2i_adapter
pip install -r requirements.txt
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/dreambooth.md

Commands to clone the repository, install the library from source, and install the specific requirements for DreamBooth training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/dreambooth
pip install -r requirements.txt
```

--------------------------------

### RL Environment Setup Requirements

Source: https://github.com/huggingface/diffusers/blob/main/examples/reinforcement_learning/README.md

Provides the necessary pip installation commands to set up the environment for running the RL examples, including PyTorch, MuJoCo, and D4RL dependencies.

```shell
pip install -f https://download.pytorch.org/whl/torch_stable.html \
                free-mujoco-py \
                einops \
                gym==0.24.1 \
                protobuf==3.20.1 \
                git+https://github.com/rail-berkeley/d4rl.git \
                mediapy \
                Pillow==9.0.0
```

--------------------------------

### Install Diffusers Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/research_projects/autoencoderkl/README.md

Installs the diffusers library from source and its training-specific requirements. This ensures compatibility with the latest example scripts. It involves cloning the repository, installing the base library, and then installing requirements from the example folder.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
pip install -r requirements.txt
accelerate config
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/research_projects/wuerstchen/text_to_image/README.md

Clones the diffusers repository, installs the library from source, and installs training dependencies for the Würstchen example.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/wuerstchen/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Install FLUX Requirements

Source: https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_flux.md

Installs the specific requirements for running the FLUX ControlNet training example. This should be done after installing the main diffusers library from source.

```bash
cd examples/controlnet
pip install -r requirements_flux.txt
```

--------------------------------

### Install Gradio

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_diffusion/overview.md

Installs the Gradio library, which is necessary for creating web demos. This is a prerequisite for the following code examples.

```shell
pip install -U gradio
```

--------------------------------

### Install Custom Diffusion Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/custom_diffusion.md

Installs the necessary Python dependencies for the Custom Diffusion example script, including clip-retrieval.

```bash
cd examples/custom_diffusion
pip install -r requirements.txt
pip install clip-retrieval
```

--------------------------------

### Launch Training with Local Image Directory

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/create_dataset.md

Demonstrates how to initiate a training script by pointing to a local directory containing image files. This method utilizes the ImageFolder builder to automatically process the dataset structure.

```bash
accelerate launch train_unconditional.py \
    --train_data_dir <path-to-train-directory> \
    <other-arguments>
```

--------------------------------

### Install Diffusers and Dependencies (Bash)

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md

Clones the diffusers repository, installs it in editable mode, and then installs specific requirements for the SANA DreamBooth example. This ensures you have the latest code and necessary packages.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/dreambooth
pip install -r requirements_sana.txt
```

--------------------------------

### Initialize and Configure Sequential Pipeline

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/modular_diffusers/quickstart.md

Demonstrates how to initialize a pipeline using a components manager and dynamically load a ControlNet model into the pipeline components.

```python
pipeline = blocks.init_pipeline("Qwen/Qwen-Image", components_manager=manager)
pipeline.load_components(torch_dtype=torch.bfloat16)
controlnet_spec = pipeline.get_component_spec("controlnet")
controlnet_spec.pretrained_model_name_or_path = "InstantX/Qwen-Image-ControlNet-Union"
controlnet = controlnet_spec.load(torch_dtype=torch.bfloat16)
pipeline.update_components(controlnet=controlnet)
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README.md

Installs the diffusers library from source and its example-specific requirements for DreamBooth training. This ensures you have the latest versions for running the example scripts.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/dreambooth
pip install -r requirements.txt
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/text2image.md

Commands to clone the repository, install the library from source, and install the specific requirements for the text-to-image training script.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/text_to_image
pip install -r requirements.txt
```

--------------------------------

### Launch Training with Hub Dataset

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/create_dataset.md

Demonstrates how to run a training script using a dataset hosted on the Hugging Face Hub by specifying the dataset name.

```bash
accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
  --pretrained_model_name_or_path="stable-diffusion-v1-5/stable-diffusion-v1-5" \
  --dataset_name="name_of_your_dataset" \
  <other-arguments>
```

--------------------------------

### Install Dependencies for Cosmos Predict 2.5 LoRA Fine-tuning

Source: https://github.com/huggingface/diffusers/blob/main/examples/cosmos/README.md

Installs the diffusers library from source and example-specific dependencies, including requirements for the cosmos example.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e ".[dev]"
cd examples/cosmos
pip install -r requirements.txt
```

--------------------------------

### Install Necessary Libraries

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_diffusion/sdxl_turbo.md

Installs the required libraries for using the diffusers library, including diffusers, transformers, and accelerate. This is a prerequisite for running the code examples.

```python
# uncomment to install the necessary libraries in Colab
#!pip install -q diffusers transformers accelerate
```

--------------------------------

### Initialize and Run HunyuanVideo-1.5 Pipeline

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/hunyuan_video15.md

Demonstrates how to load the HunyuanVideo15Pipeline, enable memory-saving techniques like model CPU offloading and VAE tiling, and generate a video from a text prompt.

```python
import torch
from diffusers import AutoModel, HunyuanVideo15Pipeline
from diffusers.utils import export_to_video


pipeline = HunyuanVideo15Pipeline.from_pretrained(
    "HunyuanVideo-1.5-Diffusers-480p_t2v",
    torch_dtype=torch.bfloat16,
)

# model-offloading and tiling
pipeline.enable_model_cpu_offload()
pipeline.vae.enable_tiling()

prompt = "A fluffy teddy bear sits on a bed of soft pillows surrounded by children's toys."
video = pipeline(prompt=prompt, num_frames=61, num_inference_steps=30).frames[0]
export_to_video(video, "output.mp4", fps=15)
```

--------------------------------

### Install Optimum-Quanto and Accelerate

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/quantization/quanto.md

Installs the necessary libraries, optimum-quanto and accelerate, for using the Quanto backend with Diffusers.

```shell
pip install optimum-quanto accelerate
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/controlnet.md

Commands to clone the repository, install the library from source, and install the specific requirements for ControlNet training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
cd examples/controlnet
pip install -r requirements.txt
```

--------------------------------

### Install Diffusers Library

Source: https://github.com/huggingface/diffusers/blob/main/README.md

Commands to install the Diffusers library using popular package managers. This setup is required to access the library's core functionalities.

```bash
pip install --upgrade diffusers[torch]
```

```sh
conda install -c conda-forge diffusers
```

--------------------------------

### Install Diffusers from Source and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md

Installs the diffusers library from its GitHub repository and specific training requirements for SD3 DreamBooth. This ensures the latest example scripts are used.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
pip install -r examples/dreambooth/requirements_sd3.txt
```

--------------------------------

### Launch Training with Gradient Accumulation

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/t2i_adapters.md

Example command to launch the training script using accelerate with specific parameters like gradient accumulation steps.

```bash
accelerate launch train_t2i_adapter_sdxl.py \
  --gradient_accumulation_steps=4
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README.md

Installs the diffusers library from source and its example-specific requirements. This is recommended for using the latest example scripts. It also configures the Accelerate environment for distributed training.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
pip install -r requirements.txt
accelerate config
```

```python
from accelerate.utils import write_basic_config
write_basic_config()
```

--------------------------------

### Install Diffusers from source

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/wuerstchen.md

Clone the repository and install the library in editable mode.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install .
```

--------------------------------

### Install DreamBooth Flux Requirements

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md

Installs the specific Python dependencies required for running the DreamBooth Flux training examples. This should be run after cloning the diffusers repository and navigating to the examples/dreambooth directory.

```bash
pip install -r requirements_flux.txt
```

--------------------------------

### Install Diffusers Training Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md

Installs the diffusers library from source and specific requirements for SDXL ControlNet training. This ensures you have the latest code and necessary dependencies for running the example scripts.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
cd examples/controlnet
pip install -r requirements_sdxl.txt
```

--------------------------------

### Install Diffusers and Dependencies

Source: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_qwen.md

Installs the diffusers library from source and its specific training dependencies for DreamBooth examples. It also includes commands for configuring Accelerate for distributed training and initializing an Accelerate environment.

```bash
git clone https://github.com/huggingface/diffusers
cd diffusers
pip install -e .
pip install -r examples/dreambooth/requirements_sana.txt
accelerate config
accelerate config default
```

--------------------------------

### Initialize Accelerate Configuration

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/training/lora.md

Sets up the 🤗 Accelerate environment for distributed training. This can be done interactively or with default settings.

```bash
accelerate config
```

```bash
accelerate config default
```

--------------------------------

### AnimateDiff with FreeInit

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/animatediff.md

This example shows how to integrate the FreeInit method into the AnimateDiff pipeline to improve temporal consistency and video quality without additional training.

```APIDOC
## Using FreeInit

### Description
Demonstrates the integration of FreeInit, a method to enhance temporal consistency and quality in videos generated by diffusion models, with the AnimateDiff pipeline. FreeInit refines the latent-initialization noise iteratively without requiring extra training.

### Method
POST (Conceptual - This is a Python script, not a direct API endpoint)

### Endpoint
N/A (Python script execution)

### Parameters
N/A (Python script parameters)

### Request Example
```python
import torch
from diffusers import MotionAdapter, AnimateDiffPipeline, DDIMScheduler
from diffusers.utils import export_to_gif

# Load motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")

# Load base model and pipeline
model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, torch_dtype=torch.float16).to("cuda")

# Configure scheduler
pipe.scheduler = DDIMScheduler.from_pretrained(
    model_id,
    subfolder="scheduler",
    beta_schedule="linear",
    clip_sample=False,
    timestep_spacing="linspace",
    steps_offset=1
)

# Enable memory savings
pipe.enable_vae_slicing()
pipe.enable_vae_tiling()

# Enable FreeInit
# Refer to the enable_free_init documentation for a full list of configurable parameters
pipe.enable_free_init(method="butterworth", use_fast_sampling=True)

# Run inference
output = pipe(
    prompt="a panda playing a guitar, on a boat, in the ocean, high quality",
    negative_prompt="bad quality, worse quality",
    num_frames=16,
    guidance_scale=7.5,
    num_inference_steps=20,
    generator=torch.Generator("cpu").manual_seed(666),
)
```

### Response
#### Success Response (200)
- **frames** (List[PIL.Image.Image]) - A list of generated video frames.

#### Response Example
```json
{
  "frames": [
    "<image data>",
    "<image data>",
    ...
  ]
}
```
```

--------------------------------

### Enable FreeU for Zeroscope

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/using-diffusers/image_quality.md

This example demonstrates how to enable and configure FreeU for the Zeroscope pipeline. It shows the necessary imports, pipeline loading, and FreeU activation with specific scaling factors.

```APIDOC
## Enable FreeU for Zeroscope

### Description
This example demonstrates how to enable and configure FreeU for the Zeroscope pipeline. It shows the necessary imports, pipeline loading, and FreeU activation with specific scaling factors.

### Method
`pipeline.enable_freeu(s1, s2, b1, b2)`

### Parameters
#### Query Parameters
- **s1** (float) - Optional - Scaling factor for skip connections stage 1.
- **s2** (float) - Optional - Scaling factor for skip connections stage 2.
- **b1** (float) - Optional - Scaling factor for backbone stage 1.
- **b2** (float) - Optional - Scaling factor for backbone stage 2.

### Request Example
```python
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video

pipeline = DiffusionPipeline.from_pretrained(
    "damo-vilab/text-to-video-ms-1.7b", torch_dtype=torch.float16
).to("cuda")
# FreeU configuration would follow here, similar to other pipelines.
# Example: pipeline.enable_freeu(s1=0.9, s2=0.2, b1=1.3, b2=1.4)
```

### Response
#### Success Response (200)
- **video** (str) - Path to the exported video file.

#### Response Example
```json
{
  "video": "path/to/exported/video.mp4"
}
```
```

--------------------------------

### Install TensorFlow and Tensorboard for Profiling

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/zh/training/controlnet.md

Install necessary libraries for performance profiling with Flax, including TensorFlow and Tensorboard's profiling plugin.

```bash
pip install tensorflow tensorboard-plugin-profile
```

--------------------------------

### Setup TPU Software Environment

Source: https://github.com/huggingface/diffusers/blob/main/examples/research_projects/pytorch_xla/training/text_to_image/README.md

Installs PyTorch, PyTorch/XLA nightly builds, and necessary dependencies on the TPU worker nodes via SSH.

```bash
gcloud compute tpus tpu-vm ssh ${TPU_NAME} --project=${PROJECT_ID} --zone=${ZONE} --worker=all --command='pip3 install --pre torch==2.6.0.dev20241031+cpu torchvision --index-url https://download.pytorch.org/whl/nightly/cpu
pip3 install "torch_xla[tpu] @ https://storage.googleapis.com/pytorch-xla-releases/wheels/tpuvm/torch_xla-2.6.0.dev20241031.cxx11-cp310-cp310-linux_x86_64.whl" -f https://storage.googleapis.com/libtpu-releases/index.html
pip install torch_xla[pallas] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html'
```

--------------------------------

### Environment Setup for Diffusers

Source: https://github.com/huggingface/diffusers/blob/main/examples/community/README.md

Commands to clone the repository, create a Conda environment, and install all required dependencies including PyTorch, Detectron2, and Diffusers.

```Shell
git clone https://github.com/huggingface/diffusers.git
cd diffusers

conda create --name ami python=3.9 -y
conda activate ami

conda install pytorch==1.10.1 torchvision==0.11.2 torchaudio==0.10.1 cudatoolkit=11.3 -c pytorch -c conda-forge -y
python -m pip install detectron2==0.6 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu113/torch1.10/index.html
pip install easydict
pip install diffusers==0.20.2 accelerate safetensors transformers
pip install setuptools==59.5.0
pip install opencv-python
pip install numpy==1.24.1
```

--------------------------------

### Create Components from Configuration

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/modular_diffusers/modular_pipeline.md

Shows how to retrieve a component specification, modify its configuration, and instantiate the component for the pipeline.

```python
guider_spec = pipeline.get_component_spec("guider")
guider_spec.config = {"guidance_scale": 5.0}
guider = guider_spec.create()
pipeline.update_components(guider=guider)
```

--------------------------------

### Install sd_embed library

Source: https://github.com/huggingface/diffusers/blob/main/docs/source/en/using-diffusers/weighted_prompts.md

Installs the required sd_embed library directly from the GitHub repository using uv.

```bash
!uv pip install git+https://github.com/xhinker/sd_embed.git@main
```