WorldFoundry
English中文

Video · image-to-video · long-video-generation · depth-controlled-video · trajectory-controlled-video

LongVie 2

Vchitect

WorldFoundry vendors the official LongVie DiffSynth runtime under worldfoundry/synthesis/visual_generation/longvie/longvie_runtime.

IntegratedUnified environmentlongvie-2

Build your run

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

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

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
pending
Environment
worldfoundry-unified-cu128
Python
3.10
CUDA
CUDA 12.8
PyTorch
torch
Source revision
—
Checkpoint revision
dd061bbd6d2084fa474d8d66bbbfbfb790d0fde3
Runtime profile
longvie-2
Pipeline binding
longvie-2
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.longvie.pipeline_longvie:LongVie2Pipeline
Backend stage
in_tree_runtime
Runtime status
checkpoint_assets_pending_not_runnable_until_staged
Driver status
compatible
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 longvie-2
Package constraints 21
  • torch
  • torchvision
  • transformers>=4.57.0,<5
  • accelerate
  • peft
  • imageio
  • imageio[ffmpeg]
  • safetensors
  • einops
  • sentencepiece
  • protobuf
  • modelscope
  • ftfy
  • pynvml
  • pandas
  • decord
  • pillow
  • numpy
  • opencv-python
  • huggingface_hub
  • xfuser
Conda packages 5
  • python=3.10
  • 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 longvie-2 --check-local --json
Vchitect/LongVie2
Revision
—
License
—
Gated
—
Private
—
Wan-AI/Wan2.1-I2V-14B-480P
Revision
—
License
—
Gated
—
Private
—
Vchitect/LongVie2
Revision
dd061bbd6d2084fa474d8d66bbbfbfb790d0fde3
License
—
Gated
—
Private
—
Wan-AI/Wan2.1-I2V-14B-480P
Revision
6b73f84e66371cdfe870c72acd6826e1d61cf279
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 longvie-2 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/longvie-2 \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
controlsdense_depth_video_per_segment, sparse_pointmap_or_track_video_per_segment
imageRequired
promptRequired
videoRequired

Artifact contract

Artifact kindFilename / path
generated_video—
generated_videolongvie-2.mp4
05

Evidence & sources

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

Integration
integrated
Runner evidence
pending
Native demo evidence
Not recorded
Validation imports
torch, torchvision, transformers>=4.57.0,<5, accelerate, peft, imageio, safetensors, einops, sentencepiece, modelscope, ftfy, pynvml, pandas, decord, PIL, numpy, cv2, xfuser
Recipe provenance
worldfoundry/data/models/catalog/video/longvie-2.yamlProjecthttps://vchitect.github.io/LongVie2-project/GitHubhttps://github.com/Vchitect/LongVieHugging Facehttps://huggingface.co/Vchitect/LongVie2Hugging Facehttps://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P