### Launch Frontend

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/scripts/launch/README.md

Starts the Next.js frontend. Installs npm dependencies if node_modules/ is missing.

```bash
apps/dreamverse/scripts/launch/launch_frontend.sh
```

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

### Verify FastVideo Setup

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/developer_env/runpod.md

Run these commands to verify that FastVideo is installed correctly and the tests pass.

```bash
cd /FastVideo
python -c "import fastvideo; print('OK')"
pytest tests/ -q --no-header
```

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

### Run FastVideo UI Application

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/ui/README.md

Standard commands to install dependencies and start the web application from the ui directory.

```bash
cd ui
npm install
npm run build
npm run start
```

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

### Launch Dreamverse Backend Servers

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/dreamverse-development.md

Start the migrated Dreamverse backend server or its mock version. Use the installed console commands.

```bash
dreamverse-server --port 8009
```

```bash
dreamverse-mock-server --port 8009
```

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

### Install FFmpeg for Mock Backend

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Install FFmpeg or set FASTVIDEO_FFMPEG_BIN to an FFmpeg binary path to resolve mock backend startup failures. Use the native FFmpeg installer for non-mock local GPU streaming.

```bash
FASTVIDEO_FFMPEG_BIN
```

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

### Install and Configure Modal CLI

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/scripts/modal/README.md

Install the Modal CLI and set up your workspace token and profile.

```bash
pip install modal
modal token set --token-id <token-id> --token-secret <token-secret> --profile=<profile-name>
modal profile activate <profile-name>
```

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

### Generate Video from Image Prompt

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/inference_quick_start.md

Generate a video starting from an initial image. This example sets up the generator and sampling parameters, including the image path and desired number of frames, before generating the video.

```python
from fastvideo import VideoGenerator, SamplingParam

def main():
    # Create the generator
    model_name = "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers"
    generator = VideoGenerator.from_pretrained(model_name, num_gpus=1)

    # Set up parameters with an initial image
    sampling_param = SamplingParam.from_pretrained(model_name)
    sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
    sampling_param.num_frames = 107

    # Generate video based on the image
    prompt = "A photograph coming to life with gentle movement"
    generator.generate_video(prompt, sampling_param=sampling_param,
                             output_path="my_videos/",
                             save_video=True)

if __name__ == '__main__':
    main()
```

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

### Install fastvideo.eval with Just VBench

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs only the VBench metrics, with an option to include additional metrics by installing detectron2.

```bash
uv pip install -e .[eval-vbench]
```

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

### Install fastvideo.eval with Just Physics-IQ

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs only the Physics-IQ metrics, which are also covered by the default [eval] installation.

```bash
uv pip install -e .[eval-physics-iq]
```

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

### Install SageAttention from Source

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/optimizations.md

Compiles and installs the SageAttention library from its GitHub repository. This is a prerequisite for using SageAttention 2.1.1.

```bash
git clone https://github.com/thu-ml/SageAttention.git
cd sageattention
python setup.py install  # or uv pip install -e .

```

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

### Run React Development Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/performance_dashboard/README.md

Navigate to the frontend directory, install dependencies, and start the React development server. Vite will proxy API requests to the FastAPI server.

```bash
cd performance_dashboard/frontend
npm install
npm run dev
```

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

### Install Dependencies and Serve Docs

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/README.md

Installs project dependencies using uv pip and serves the documentation with live reload for development. Alternatively, it can build a static site.

```bash
uv pip install -r requirements-mkdocs.txt

mkdocs serve

# Or build static site
mkdocs build
```

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

### Install Default fastvideo.eval

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs the default evaluation suite, including common metrics, optical flow, VBench, Physics-IQ, and videoscore2.

```bash
uv pip install -e .[eval]
```

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

### Install fastvideo.eval with Audio Metrics

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs all audio-related metrics, including CLAP, FAD, KL, WER, AudioBox, DeSync, and ImageBind.

```bash
uv pip install -e .[eval-audio]
```

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

### Install FastVideo from Source

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation/gpu.md

Installs FastVideo from its source code using uv. This is typically done after cloning the repository.

```bash
uv pip install -e .
```

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

### Install FastVideo with uv

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/README.md

Use uv to create a new environment and install FastVideo. Ensure Python 3.12 is used for a seeded environment.

```bash
uv venv --python 3.12 --seed
source .venv/bin/activate

uv pip install fastvideo
```

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

### Install and Run Pre-commit Hooks

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/pull_requests.md

Install the pre-commit framework and run all checks on your files to identify and fix potential issues before committing.

```bash
# Install pre-commit if needed
uv pip install pre-commit
pre-commit install

# Run all checks on all files
pre-commit run --all-files
```

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

### Install FastVideo with uv

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation.md

Use uv for faster and more stable installations. This snippet creates and activates a new uv environment, then installs FastVideo.

```bash
# Create and activate a new uv environment
uv venv --python 3.12 --seed
source .venv/bin/activate

uv pip install fastvideo
```

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

### Install Dreamverse from Source

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Installs Dreamverse by cloning the repository and installing from source using uv. This method requires Git and Python 3.12.

```bash
git clone https://github.com/hao-ai-lab/FastVideo.git
cd FastVideo

pip install --upgrade pip
pip install uv
uv venv .venv --python 3.12
source .venv/bin/activate
uv pip install -e ".[dreamverse]"
```

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

### Install FastVideo Dependency

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/comfyui/README.md

Install the 'fastvideo' Python package using uv.

```bash
uv pip install fastvideo
```

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

### Install Flash Attention 2

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/optimizations.md

Install Flash Attention 2 using pip. This is recommended for most GPUs.

```bash
uv pip install flash-attn==2.7.4.post1 --no-build-isolation
```

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

### Install Dreamverse from PyPI

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Use this command to install the Dreamverse extra from PyPI.

```bash
uv pip install "fastvideo[dreamverse]"
```

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

### Install Full fastvideo.eval Suite

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs the complete evaluation suite, combining the default [eval] with audio metrics and the VBench scene metric (AVoCaDO).

```bash
uv pip install -e .[eval-full]
```

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

### Run NVFP4 + Attn-QAT Example Script

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/optimizations.md

Executes the example script for NVFP4 + Attn-QAT optimization. An optional flag is provided to run the baseline comparison using BF16.

```bash
python examples/inference/optimizations/nvfp4_qat_wan2_1_1_3b.py
python examples/inference/optimizations/nvfp4_qat_wan2_1_1_3b.py --bf16  # baseline

```

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

### Install Production-Equivalent Prerequisites

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/dreamverse-development.md

Install necessary dependencies for the production-equivalent NVFP4 path before running GPU smoke tests. This command installs packages into the FastVideo .venv.

```bash
uv pip install --python .venv/bin/python \
  flashinfer-python flash-attn cerebras-cloud-sdk openai \
  --no-build-isolation
```

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

### Install FastVideo with Development Dependencies

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/design/training_architecture.md

Installs FastVideo and its development dependencies using uv pip.

```bash
# Install
uv pip install -e ".[dev]"
```

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

### Install system dependencies

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/attention/index.md

Install required compilers and build tools on Ubuntu-based systems.

```bash
sudo apt update
sudo apt install -y gcc-11 g++-11 clang-11 ninja-build

# Set gcc-11 as default
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 100 --slave /usr/bin/g++ g++ /usr/bin/g++-11
```

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

### Run FP8 Quantization Example Script

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/optimizations.md

Execute the example script for FP8 quantization with different granularity settings or as a baseline using bf16.

```bash
python examples/inference/optimizations/fp8_wan2_1_1_3b.py
python examples/inference/optimizations/fp8_wan2_1_1_3b.py --granularity channel
python examples/inference/optimizations/fp8_wan2_1_1_3b.py --bf16  # baseline

```

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

### Install FastVideo with Dreamverse Extra

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/dreamverse-development.md

Install the FastVideo package with the 'dreamverse' extra if 'dreamverse-server' is missing. This command should be run from the FastVideo repository root.

```bash
uv pip install -e ".[dreamverse]"
```

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

### Run New API Inference Example

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/inference/basic/README.md

Run the example that utilizes the typed config/request path introduced during the inference API refactor.

```bash
python examples/inference/basic/basic_dmd_new_api.py
```

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

### Install ffmpeg

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/comfyui/README.md

Install ffmpeg using apt-get if you encounter 'ImportError: libGL.so.1: cannot open shared object file: No such file or directory'.

```bash
apt-get update && apt-get install ffmpeg
```

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

### Install and Run Pre-commit Hooks

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/overview.md

Installs pre-commit hooks for linting, formatting, and static typing, then runs all hooks on the entire project to ensure code quality.

```bash
pre-commit install --hook-type pre-commit --hook-type commit-msg
pre-commit run --all-files
```

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

### Clone Official Reference and Install

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/tests/local_tests/gamecraft/README.md

Clone the official reference repository and install it locally. Ensure core dependency versions are not changed without approval.

```bash
git clone <official_repo_url> Hunyuan-GameCraft-1.0
uv pip install --no-deps -e ./Hunyuan-GameCraft-1.0
```

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

### Source FFmpeg Environment and Start Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Sources the generated FFmpeg environment script to use the custom FFmpeg binary and then starts the Dreamverse server. This is necessary for non-Docker installs.

```bash
source apps/dreamverse/scripts/ffmpeg-env.sh
dreamverse-server
```

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

### Serve Docs Locally

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/README.md

Starts a local development server for viewing the documentation with live reload. Access the docs via the provided URL.

```bash
mkdocs serve
```

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

### Pull Request Title Format Examples

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/pull_requests.md

Examples of valid pull request titles using different type tags. Ensure your PR title starts with one of these tags enclosed in square brackets.

```text
[feat] Add causal Wan 2.2 I2V pipeline
```

```text
[bugfix] Fix VAE temporal tiling corruption on H100
```

```text
[refactor] Restructure distributed attention dispatch
```

```text
[docs] Add LoRA finetuning guide
```

```text
[new-model] Port HunyuanVideo 1.5 to FastVideo
```

```text
[infra] Add activation trace hooks for pipeline debugging
```

```text
[skill] Add add-model agent skill
```

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

### RunPod Custom Template Container Start Command

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/developer_env/runpod.md

This command is used as the Container Start Command in RunPod for custom templates to enable SSH access. It installs OpenSSH server and configures it to accept your public key.

```bash
bash -c "apt update;DEBIAN_FRONTEND=noninteractive apt-get install openssh-server -y;mkdir -p ~/.ssh;cd $_;chmod 700 ~/.ssh;echo \"$PUBLIC_KEY\" >> authorized_keys;chmod 700 authorized_keys;service ssh start;sleep infinity"
```

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

### Launch Training with Helper Script

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/training/train_infra.md

Use the provided bash script to launch training with a specified configuration file. The script automatically detects GPUs and sets up torchrun.

```bash
bash examples/train/run.sh examples/train/distill_wan2.1_t2v_1.3B_dmd2.yaml
```

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

### Train Wan2.2 5B Model

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/distillation/dmd.md

Start a multi-node training process for the Wan2.2 5B model using Sparse-Distill. This script is intended for distributed training setups.

```bash
# Multi-node training (8 nodes, 64 GPUs total)
sbatch examples/distill/Wan2.2-TI2V-5B-Diffusers/Data-free/distill_dmd_t2v_5B.sh
```

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

### Launch FastVideo Backend for Serve-Config Checks

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/scripts/launch/README.md

Starts the typed fastvideo serve --config path for lower-level checks. Not a full Dreamverse app replacement.

```bash
apps/dreamverse/scripts/launch/launch_backend_fastvideo.sh
```

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

### Install Miniconda for ARM64

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation/mps.md

Downloads and installs the Miniconda installer for macOS ARM64 systems.

```bash
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh
bash Miniconda3-latest-MacOSX-arm64.sh
source ~/.zshrc
```

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

### Install VSA

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/distill/Wan2.1-T2V/Wan-Syn-Data-480P/README.md

Installs the VSA package using pip. Ensure you have Python and pip installed.

```bash
uv pip install vsa
```

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

### Run Basic Video Generation Example on Apple Silicon

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/inference/basic/README.md

Use this command to run the basic video generation example on Apple silicon hardware, utilizing MPS for acceleration.

```bash
python examples/inference/basic/basic_mps.py
```

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

### Install VSA Library

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/distill/Wan2.2-TI2V-5B-Diffusers/crush_smol/README.md

Installs the VSA library using pip. Ensure you have Python and pip installed.

```bash
uv pip install vsa

```

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

### Install Optional Inference Dependencies

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/tests/local_tests/stable_audio/README.md

Install necessary inference dependencies like k_diffusion and friends. These are not part of the base FastVideo installation.

```bash
uv pip install k_diffusion einops_exts alias_free_torch torchsde
```

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

### Install FastVideo with Conda

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation.md

An alternative installation method using Conda to create and activate an environment, then installing FastVideo via uv.

```bash
# Create and activate a new conda environment
conda create -n fastvideo python=3.12 -y
conda activate fastvideo

uv pip install fastvideo
```

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

### Initialize Video Generation Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/design/server_contracts/dynamo.md

Sets up and starts the video generation service. It initializes the VideoGenerator, configures the endpoint, and handles graceful shutdown and health checks.

```python
async def init_video_generation(runtime, config, shutdown_endpoints):
    from fastvideo import VideoGenerator
    from fastvideo.api import config_to_dict

    server_args, dynamo_args = config.server_args, config.dynamo_args
    generator = VideoGenerator.from_pretrained(**config.fastvideo_kwargs())

    dump_config(dynamo_args.dump_config_to, config)

    endpoint = runtime.endpoint(
        f"{dynamo_args.namespace}.{dynamo_args.component}.{dynamo_args.endpoint}"
    )
    shutdown_endpoints[:] = [endpoint]

    handler = VideoGenerationWorkerHandler(
        generator, config, fs=get_fs(dynamo_args.media_output_fs_url)
    )
    payload = FastVideoHealthCheckPayload(generator).to_dict()

    await asyncio.gather(
        endpoint.serve_endpoint(
            handler.generate,
            graceful_shutdown=True,
            health_check_payload=payload,
        ),
        register_video_generation_model(
            generator, endpoint, server_args,
        ),
    )
```

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

### Build Static Site and Serve Locally

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/README.md

Builds a static version of the documentation and serves it using Python's built-in HTTP server. Access the docs via the provided URL.

```bash
mkdocs build
python -m http.server -d site/
```

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

### Install from Source with Conda Environment

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation.md

Installs FastVideo from source within a Conda environment, still utilizing uv for package management. Includes optional flash-attn installation.

```bash
uv pip install -e .
uv pip install flash-attn --no-build-isolation -v
```

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

### Overriding setup and to Methods

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/contributing/eval-metrics.md

Provides optional methods to override for metric setup and device management. `setup` is for eager model loading, and `to` is for moving the metric and its submodels to a specified device.

```python
# You may override:
# - setup(self) -> None. Eager model loading. Called once by
#   `create_evaluator`. Idempotent (re-entrant). Use the `if self._model
#   is not None: return` pattern.
# - to(self, device). Move the metric and its submodels to `device`.
```

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

### Run FastVideo Gradio Local Demo

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/inference/gradio/local/README.md

Execute this command to start the Gradio web interface for local video generation. The demo will be accessible at http://0.0.0.0:7860.

```bash
python examples/inference/gradio/local/gradio_local_demo.py
```

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

### Install FFmpeg Dependency

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation/mps.md

Installs the FFmpeg multimedia framework using Homebrew.

```bash
brew install ffmpeg
```

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

### Run FastLTX-2.3 Gradio Local Demo

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/inference/gradio/local/gradio_local_demo_ltx2_3/README.md

Navigate to the examples directory and run the Gradio local demo using Python. Ensure you have the necessary GPU requirements.

```bash
cd examples/inference/gradio/local
python -m gradio_local_demo_ltx2_3 --port 7860
```

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

### Install Detectron2 for VBench

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo/eval/README.md

Installs detectron2 with no-build-isolation, required for certain VBench metrics.

```bash
uv pip install --no-build-isolation 'git+https://github.com/facebookresearch/detectron2.git'
```

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

### Start Mock Dreamverse Backend Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Initiate the mock backend server for UI development. This allows frontend development without a GPU by emulating the backend protocol and streaming synthetic video.

```bash
dreamverse-mock-server --latency 200 --port 8009
```

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

### Download and Preprocess Dataset

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/training/data_preprocess.md

Downloads a sample dataset and executes the preprocessing script.

```bash
# Download the crush-smol dataset
python scripts/huggingface/download_hf.py \
    --repo_id "wlsaidhi/crush-smol-merged" \
    --local_dir "data/crush-smol" \
    --repo_type "dataset"

# Run preprocessing
bash examples/training/finetune/wan_t2v_1.3B/crush_smol/preprocess_wan_data_t2v_new.sh
```

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

### Install Extension Library

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/fastvideo-kernel/CMakeLists.txt

Installs the compiled extension library to 'fastvideo_kernel/_C' to enable its loading and registration of operations.

```cmake
# We install it to fastvideo_kernel/_C so we can load it to register the ops
install(TARGETS fastvideo_kernel_ops LIBRARY DESTINATION fastvideo_kernel/_C)
```

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

### Run FastVideo API Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/ui/README.md

Command to start the API server from the root directory with custom output and log paths.

```bash
python -m ui.server --output-dir /path/to/videos --log-dir /path/to/logs
```

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

### Install Web Dependencies

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Install frontend web dependencies using npm. Ensure you are in the `apps/dreamverse/web` directory.

```bash
cd apps/dreamverse/web
npm ci
```

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

### Example Training Scenario Directory Structure

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/train/scenario/README.md

Illustrates the directory layout for a multi-step training scenario, including a specific example for KD → export → Self-Forcing.

```directory
scenario/
└── ode_init_self_forcing_wan_causal/   # KD → export → Self-Forcing
```

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

### Start Frontend Development Server

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/README.md

Start the frontend development server. Ensure the `BACKEND_HOST` and `BACKEND_PORT` environment variables are set correctly. Access the frontend at `http://localhost:5299`.

```bash
cd apps/dreamverse/web
BACKEND_HOST=localhost BACKEND_PORT=8009 npm run dev
```

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

### Install FP4 Flash Attention 4 (Blackwell)

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/optimizations.md

Install the FP4 Flash Attention 4 kernel for Blackwell GPUs. Use --no-deps to avoid upgrading existing torch installations. Requires torch >= 2.4 with CUDA 12.8+.

```bash
pip install --no-deps "git+ssh://git@github.com/hao-ai-lab/flash-attention-fp4.git@fp4#subdirectory=flash_attn/cute"
pip install "nvidia-cutlass-dsl>=4.4.2" apache-tvm-ffi flashinfer-python
```

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

### Launch Dreamverse Backend

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/apps/dreamverse/scripts/launch/README.md

Starts the full Dreamverse backend path required by the web application.

```bash
apps/dreamverse/scripts/launch/launch_backend_dreamverse.sh
```

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

### Run Basic Video Generation Example

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/examples/inference/basic/README.md

Execute the basic Python script to generate a video using the VideoGenerator. This script demonstrates the simplest way to use FastVideo.

```bash
python examples/inference/basic/basic.py
```

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

### Install MoGe for GEN3C

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/inference/gen3c.md

Installs the MoGe library required for GEN3C integration. Ensure you are in the correct environment before running.

```bash
uv pip install git+https://github.com/microsoft/MoGe.git
```

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

### Download and Install Miniconda

Source: https://github.com/hao-ai-lab/fastvideo/blob/main/docs/getting_started/installation/gpu.md

Downloads the latest Miniconda installer for Linux and executes it. Sources the bashrc to update the environment.

```bash
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh
source ~/.bashrc
```