WorldFoundry
English中文

Video · text-to-audio · video-to-audio · audio-generation

MMAudio

Worldfoundry Native

WorldFoundry route is complete; missing checkpoint/assets are reported at runtime.

IntegratedUnified environmentmmaudio

Build your run

Choose a recorded variant, then copy the exact setup or inspection command.

worldfoundry.pipeline
Tasktext-to-audio
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id mmaudio \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/mmaudio \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
pending
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
—
Checkpoint revision
—
Runtime profile
mmaudio
Pipeline binding
mmaudio
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.video_official.pipeline_official_video:MMAudioPipeline
Backend stage
official_runtime_bridge
Runtime status
integrated_checkpoint_required
Driver status
compatible_unified_default
Environment kind
Unified environment
02

Install environment

The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.

bash scripts/setup/model_env_install.sh --model mmaudio
Package constraints 19
  • torch
  • torchvision
  • torchaudio
  • av
  • numpy
  • pillow
  • scipy
  • tqdm
  • einops
  • huggingface_hub
  • torchdiffeq
  • open_clip_torch
  • colorlog
  • librosa
  • soundfile
  • hydra-core
  • hydra_colorlog
  • tensordict
  • python-dotenv
Conda packages 3
  • python=3.11
  • pip
  • ffmpeg
03

Checkpoints & assets

Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.

worldfoundry-eval zoo model-download --model-id mmaudio --check-local --json
hkchengrex/MMAudio
Revision
—
License
—
Gated
—
Private
—
04

Launch & outputs

The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.

worldfoundry-eval evaluate \
  --mode model \
  --model-id mmaudio \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/mmaudio \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptRequired
videooptional

Artifact contract

Artifact kindFilename / path
generated_audiommaudio.wav
05

Evidence & sources

Catalog integration, native-demo parity, and runner parity are independent records.

Integration
integrated
Runner evidence
pending
Native demo evidence
Not recorded
Validation imports
torch, torchvision, torchaudio, av, colorlog, librosa, soundfile, torchdiffeq, open_clip, hydra, hydra_plugins.hydra_colorlog, tensordict
Recipe provenance
worldfoundry/data/models/catalog/video/mmaudio.yamlGitHubhttps://github.com/hkchengrex/MMAudio