Video · text-to-video

Open-Sora-Plan

LanguageBind

Official GitHub is PKU-YuanGroup; official HF releases are under LanguageBind.

IntegratedUnified environmentPinned sourceopen-sora-plan

Build your run

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

worldfoundry.pipeline

Variant

Tasktext-to-video

Environmentworldfoundry-unified-cu128

DeviceCUDA 12.8

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

Compatibility & versions

Manifest-backed recipe

Integration: integrated
Runner evidence: Not recorded
Environment: worldfoundry-unified-cu128
Python: 3.11
CUDA: CUDA 12.8
PyTorch: torch
Source revision: f7fa604f4e3a523d6b973e4c89a5620ed1aff65a
Checkpoint revision: cd3b49a3500b98724bd01eb00bdae59f1c247750

Runtime profile: open-sora-plan
Pipeline binding: open-sora-plan
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.video_official.pipeline_official_video:OpenSoraPlanPipeline
Backend stage: official_runtime_bridge
Runtime status: integrated_checkpoint_required
Driver status: compatible_unified_default
Environment kind: Unified environment

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 open-sora-plan

Package constraints 4

torch
torchvision
torchaudio
xfuser

Conda packages 5

python=3.11
pip
ffmpeg
setuptools
wheel

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 open-sora-plan --check-local --json

LanguageBind/Open-Sora-Plan-v1.3.0

Revision: cd3b49a3500b98724bd01eb00bdae59f1c247750
License: mit
Gated: false
Private: false

LanguageBind/Open-Sora-Plan-v1.3.0

Revision: —
License: —
Gated: —
Private: —

google/mt5-xxl

Revision: —
License: —
Gated: —
Private: —

Launch & outputs

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

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

Input contract

Field	Recorded contract
`prompt`	Required

Artifact contract

Artifact kind	Filename / path
`generated_video`	`open-sora-plan.mp4`

Evidence & sources

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

Integration: integrated
Runner evidence: Not recorded
Native demo evidence: passed
Validation imports: torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry

Recipe provenance

worldfoundry/data/models/catalog/video/open-sora-plan.yamlGitHubf7fa604f4e3a523d6b973e4c89a5620ed1aff65a

Build your run

Input contract

Artifact contract

Related recipes