WorldFoundry
English中文

3D & 4D · camera-controlled video rerendering

ReCamMaster

Kling Team / Kuaishou, Zhejiang University, CUHK, and HUST authors

WorldFoundry exposes the in-tree ReCamMaster pipeline, operator, and synthesis runtime under the Kling namespace.

Runner verifiedUnified environmentrecammaster

Build your run

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

worldfoundry.pipeline
Taskcamera-controlled video rerendering
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id recammaster \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/recammaster \
  --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
—
Checkpoint revision
4f3f7391743dfd25067ab27e0f1eb8928d11b91d
Runtime profile
recammaster
Pipeline binding
recammaster
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.kling.pipeline_recammaster:ReCamMasterPipeline
Backend stage
in_tree_runtime
Runtime status
official_camera_video_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 recammaster
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 recammaster --check-local --json
KlingTeam/ReCamMaster-Wan2.1
Revision
4f3f7391743dfd25067ab27e0f1eb8928d11b91d
License
—
Gated
—
Private
—
Wan-AI/Wan2.1-T2V-1.3B
Revision
37ec512624d61f7aa208f7ea8140a131f93afc9a
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 recammaster \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/recammaster \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptRequired
imageOptional
videoRequired
actionscamera_viewpoint, camera_trajectory

Artifact contract

Artifact kindFilename / path
generated_video—
generated_4d_scene—
generated_videorecammaster.mp4
05

Evidence & sources

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

Integration
integrated
Runner evidence
verified
Native demo evidence
Not recorded
Validation imports
torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry
Recipe provenance
worldfoundry/data/models/catalog/three_d_four_d/recammaster.yamlProjecthttps://jianhongbai.github.io/ReCamMaster/Paperhttps://arxiv.org/abs/2503.11647GitHubhttps://github.com/KlingAIResearch/ReCamMaster