WorldFoundry
English中文

Video · image-to-video · text-to-video

I2VGen-XL

ali-vilab

Official GitHub and ali-vilab HF repo were both reachable.

IntegratedUnified environmentPinned sourcei2vgen-xl

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 i2vgen-xl \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/i2vgen-xl \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
Not recorded
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
1e77740b6e3f4e61410dd2d6cec75e4b2077d360
Checkpoint revision
39e1979ea27be737b0278c06755e321f2b4360d5
Runtime profile
i2vgen-xl
Pipeline binding
i2vgen-xl
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.video_official.pipeline_official_video:I2VGenXLPipeline
Backend stage
official_hf_diffusers_runtime
Runtime status
official_demo_parity_pending
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 i2vgen-xl
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 i2vgen-xl --check-local --json
ali-vilab/i2vgen-xl
Revision
39e1979ea27be737b0278c06755e321f2b4360d5
License
mit
Gated
false
Private
false
ali-vilab/i2vgen-xl
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 i2vgen-xl \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/i2vgen-xl \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptRequired
imageRequired

Artifact contract

Artifact kindFilename / path
generated_videoi2vgen-xl.mp4
05

Evidence & sources

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

Integration
integrated
Runner evidence
Not recorded
Native demo evidence
pending
Validation imports
torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry
Recipe provenance
worldfoundry/data/models/catalog/video/i2vgen-xl.yamlGitHub1e77740b6e3f4e61410dd2d6cec75e4b2077d360