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

MMAudio

Worldfoundry Native

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

Integrated统一环境mmaudio

构建运行命令

选择仓库中已记录的 variant,然后复制对应的准备、检查或运行命令。

worldfoundry.pipeline
任务text-to-audio
环境worldfoundry-unified-cu128
设备CUDA 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

兼容性与版本

由 Manifest 生成

集成状态
integrated
Runner 证据
pending
环境
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
源码 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 状态
integrated_checkpoint_required
Driver 状态
compatible_unified_default
环境类型
统一环境
02

安装环境

环境解析器会读取已记录 profile,并选择此处显示的统一或独立环境。

bash scripts/setup/model_env_install.sh --model mmaudio
依赖版本约束 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 依赖 3
  • python=3.11
  • pip
  • ffmpeg
03

Checkpoint 与资产

分配算力前先做本地检查;gated、private 与 license 字段直接来自 checkpoint manifest。

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

运行与输出

生成的命令通过共享 evaluation 边界运行,并持久保存结果 manifest 与 artifact。

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

输入契约

字段已记录契约
promptRequired
videooptional

Artifact 契约

Artifact 类型文件名 / 路径
generated_audiommaudio.wav
05

证据与来源

Catalog 集成、原生 demo parity 与 runner parity 是三条独立记录。

集成状态
integrated
Runner 证据
pending
原生 Demo 证据
未记录
验证 Imports
torch, torchvision, torchaudio, av, colorlog, librosa, soundfile, torchdiffeq, open_clip, hydra, hydra_plugins.hydra_colorlog, tensordict
配方溯源
worldfoundry/data/models/catalog/video/mmaudio.yamlGitHubhttps://github.com/hkchengrex/MMAudio