WorldFoundry
English中文

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

LongVie

Vchitect

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

IntegratedUnified environmentlongvie-1

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-1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/longvie-1 \
  --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
—
Runtime profile
longvie-1
Pipeline binding
longvie-1
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.longvie.pipeline_longvie:LongVie1Pipeline
Backend stage
in_tree_runtime
Runtime status
integrated
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-1
Package constraints 20
  • 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
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-1 --check-local --json
Vchitect/LongVie2
Revision
—
License
—
Gated
—
Private
—
Wan-AI/Wan2.1-I2V-14B-480P
Revision
—
License
—
Gated
—
Private
—
Wan-AI/Wan2.1-T2V-1.3B
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 longvie-1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/longvie-1 \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
actionsdense_video, sparse_video
imageRequired
promptRequired
videoRequired

Artifact contract

Artifact kindFilename / path
generated_video—
generated_videolongvie-1.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, accelerate, peft, imageio, safetensors, einops, sentencepiece, modelscope, ftfy, pynvml, pandas, decord, PIL, numpy, cv2
Recipe provenance
worldfoundry/data/models/catalog/video/longvie-1.yamlProjecthttps://vchitect.github.io/LongVie2-project/GitHubhttps://github.com/Vchitect/LongVie