Video · text-to-video · image-to-video

CogVideoX

THUDM

HF cardData reports Apache-2.0 for 2B and 'other' for several larger variants.

Runner verifiedUnified environmentPinned sourcecogvideox

Build your run

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

worldfoundry.pipeline
Tasktext-to-video
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id cogvideox-2b-t2v \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/cogvideox-2b-t2v \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
verified
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
7a1af7154511e0ce4e4be8d62faa8c5e5a3532d2
Checkpoint revision
1137dacfc2c9c012bed6a0793f4ecf2ca8e7ba01
Runtime profile
cogvideox-5b-t2v
Pipeline binding
cogvideox
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.cogvideox.pipeline_cogvideox_5b_t2v:CogVideoX5bT2VPipeline
Backend stage
official_in_tree_runtime
Runtime status
official_in_tree_runtime_contract
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 cogvideox-2b-t2v
Package constraints 4
  • torch
  • torchvision
  • torchaudio
  • xfuser
Conda packages 5
  • python=3.11
  • pip
  • ffmpeg
  • setuptools
  • wheel
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 cogvideox --check-local --json
THUDM/CogVideoX-2b
Revision
1137dacfc2c9c012bed6a0793f4ecf2ca8e7ba01
License
apache-2.0
Gated
false
Private
false
THUDM/CogVideoX-5b
Revision
8fc5b281006c82b82d34fd2543d2f0ebb4e7e321
License
other
Gated
false
Private
false
THUDM/CogVideoX-5b-I2V
Revision
a6f0f4858a8395e7429d82493864ce92bf73af11
License
other
Gated
false
Private
false
THUDM/CogVideoX1.5-5B
Revision
fdc5267c90b5c06492985b966e43aae984e189e0
License
other
Gated
false
Private
false
THUDM/CogVideoX1.5-5B-I2V
Revision
46c90528707aebbe69066390b4fe7e7d24c9c2a4
License
other
Gated
false
Private
false
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 cogvideox-2b-t2v \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/cogvideox-2b-t2v \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptRequired
imageOptional
videoOptional
actionsseed

Artifact contract

Artifact kindFilename / path
generated_videocogvideox-5b-t2v.mp4
05

Evidence & sources

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

Integration
integrated
Runner evidence
verified
Native demo evidence
verified
Validation imports
torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry
Recipe provenance
worldfoundry/data/models/catalog/video/cogvideox.yamlGitHub7a1af7154511e0ce4e4be8d62faa8c5e5a3532d2