WorldFoundry
English中文

Video · video-tokenization · class-conditional-image-generation · autoregressive-generation

Open-MAGVIT2

TencentARC

Runtime source is vendored in-tree and the CUDA generation wrapper is wired.

IntegratedUnified environmentopen-magvit2

Build your run

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

worldfoundry.pipeline
Taskvideo-tokenization
Environmentworldfoundry-unified-cu128
DeviceCUDA 11.3
worldfoundry-eval evaluate \
  --mode model \
  --model-id open-magvit2 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/open-magvit2 \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
checkpoint backed verified
Environment
worldfoundry-unified-cu128
Python
3.10
CUDA
CUDA 11.3
PyTorch
torch
Source revision
—
Checkpoint revision
607230591be9efcb4ec5ec9b6417b9e863f2dd2c
Runtime profile
open-magvit2
Pipeline binding
open-magvit2
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.component_pipelines:OpenMAGVIT2Pipeline
Backend stage
in_tree_runtime
Runtime status
checkpoint_backed_verified
Driver status
compatible_with_downgraded_torch
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 open-magvit2
Package constraints 15
  • torch
  • torchvision
  • lightning==2.6.1
  • jsonargparse[signatures]
  • numpy
  • tensorboard
  • tensorboardx
  • albumentations
  • omegaconf
  • einops
  • requests
  • transformers
  • lpips
  • av
  • decord
Conda packages 3
  • python
  • 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 open-magvit2 --check-local --json
TencentARC/Open-MAGVIT2
Revision
607230591be9efcb4ec5ec9b6417b9e863f2dd2c
License
apache-2.0
Gated
—
Private
—
TencentARC/Open-MAGVIT2
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 open-magvit2 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/open-magvit2 \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
class_idRequired
imageOptional
promptOptional

Artifact contract

Artifact kindFilename / path
generated_imageopen_magvit2.png
05

Evidence & sources

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

Integration
integrated
Runner evidence
checkpoint backed verified
Native demo evidence
Not recorded
Validation imports
torch, lightning, transformers, decord
Recipe provenance
worldfoundry/data/models/catalog/video/open-magvit2.yamlGitHubhttps://github.com/TencentARC/Open-MAGVIT2