WorldFoundry
English中文

LongVie 2

Method overview: Framework of LongVie 2. LongVie 2 serves as a controllable video world model that integrates both dense and sparse control signals to provide world-level guidance for enhanced controllability. A degradation-aware.

LongVie 2 from Shanghai AI Laboratory (Vchitect): image-to-video and long-video-generation; Verified; dedicated `worldfoundry-longvie-cu128`.

Edit this pageGitHubMarkdown

LongVie 2 is the second-generation controllable long-video framework from the Vchitect team, and the verified member of the pair in this catalog: Studio's default four-GPU torchrun USP route completed a checkpoint-backed run on 2026-07-28, decoding all 81 frames at 640x352. It generates queued 81-frame control-video segments where each continuation reuses the prior final frame, an eight-frame history, and the noise state.

Method overview: Framework of LongVie 2. LongVie 2 serves as a controllable video world model that integrates both dense and sparse control signals to provide world-level guidance for enhanced controllability. A degradation-aware.
Method overview: Framework of LongVie 2. LongVie 2 serves as a controllable video world model that integrates both dense and sparse control signals to provide world-level guidance for enhanced controllability. A degradation-aware.

The recorded paper is arXiv 2512.13604.

Project page: vchitect.github.io/LongVie2-project. Code: Vchitect/LongVie.

Build your run

Pipeline
LongVie2Pipelineworldfoundry.pipelines.longvie.pipeline_longvie
TaskInteractive Video interactive-video
Environmentworldfoundry-longvie-cu128
DeviceCUDA 12.8
Runnerworldfoundry.pipeline
Loadingfrom_pretrained
Invocationnative_or_standard_invocation
worldfoundry-eval run \
  longvie-2 \
  --pipeline.task-profile interactive-video \
  --json

What it is for

Use longvie-2 for catalog depth inference. The recipe writes depth under the recorded profile.

Built over canonical Wan roles (base: Wan2.1-I2V-14B-480P) plus LongVie-specific weights: the adapter loads both control.safetensors and dit.safetensors — the latter is the LongVie 2 DiT attention override that distinguishes it from LongVie-1. Official USP ring/ulysses distributed inference is supported when execute=True. It is published by Shanghai AI Laboratory (Vchitect).

Catalog tasks include image-to-video, long-video-generation, depth-controlled-video, and trajectory-controlled-video. Catalog aliases include longvie2 and longvie-v2. Documented modalities: image in, video and depth out.

Recorded evaluation entry points include ChronoMagic-Bench (Long-horizon generation suite), CameraBench (Control-driven generation benefits from camera-motion evaluation).

Runtime contract

Optional prompt, negative_prompt, input_path, interactions, and frames; artifacts generated_video and longvie-2.mp4.

CLI task profiles: interactive-video. WorldFoundry binds LongVie2Pipeline.

Family status: Verified.

Each queued segment needs a non-empty prompt plus dense depth and sparse pointmap/track control videos; the first segment also needs an image. Quality defaults: 81 frames at 16 FPS, 50 steps. The Studio profile uses four-rank USP with the complete model resident on each supported 80GB rank, and only rank zero materializes the artifact. This is queued segment generation, not keyboard realtime.

WorldFoundry implements LongVie 2 over canonical Wan roles and the shared staged runner; LongVie owns only checkpoint-shaped control and attention behavior.

LongVie 2 runs on canonical Wan components and the shared staged diffusion runner; its synthesis package owns only product assembly and LongVie-specific conditioning.

Running in WorldFoundry

The catalog launch is worldfoundry-eval run longvie-2 --pipeline.task-profile interactive-video. The command builder above switches --pipeline.task-profile among recorded tasks and still emits worldfoundry-eval run.

It runs in the dedicated environment worldfoundry-longvie-cu128 (Python 3.10, CUDA 12.8).

Recorded weight repositories include Vchitect/LongVie2, Wan-AI/Wan2.1-I2V-14B-480P, and Vchitect/LongVie2 among others. Prepare the environment and check local assets with bash scripts/inference/prepare_model_infer.sh longvie-2. Add --download to fetch missing public checkpoints.

Status: Verified.