World models · world · camera_control · world_model

WorldCam

KAIST / Adobe Research / MAUM AI

WorldCam runtime code is in-tree and the wrapper now supports load_model=False planning without external checkout dependency.

Runner verified统一环境worldcam

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

Variant

任务world

环境worldfoundry-unified-cu128

设备CUDA 12.8

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

兼容性与版本

由 Manifest 生成

集成状态: verified
Runner 证据: verified
环境: worldfoundry-unified-cu128
Python: 3.11
CUDA: CUDA 12.8
PyTorch: torch
源码 revision: —
Checkpoint revision: —

Runtime profile: worldcam
Pipeline binding: worldcam
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.worldcam.pipeline_worldcam:WorldCamPipeline
Backend stage: in_tree_runtime
Runtime 状态: official_demo_contract
Driver 状态: compatible_unified_default
环境类型: 统一环境

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 worldcam

依赖版本约束 4

torch
torchvision
torchaudio
xfuser

Conda 依赖 5

python=3.11
pip
ffmpeg
setuptools
wheel

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 worldcam --check-local --json

worldcam/worldcam

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

Wan-AI/Wan2.1-T2V-1.3B

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

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 worldcam \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/worldcam \
  --metric artifact_count \
  --json

输入契约

字段	已记录契约
`prompt`	Required
`image`	Optional
`video`	Required
`actions`	camera_pose

Artifact 契约

Artifact 类型	文件名 / 路径
`generated_world`	`worldcam.mp4`

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: verified
Runner 证据: verified
原生 Demo 证据: 未记录
验证 Imports: torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry

配方溯源

worldfoundry/data/models/catalog/world_models/worldcam.yamlProjecthttps://cvlab-kaist.github.io/WorldCam/GitHubhttps://github.com/cvlab-kaist/WorldCam

构建运行命令

输入契约

Artifact 契约

相关配方