Video · text-to-video · legacy-unet-diffusion

ZeroScope

Huggingface

CC-BY-NC-4.0 requires benchmark policy review before commercial or automated benchmark use.

Runner verifiedUnified environmentzeroscope

Build your run

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

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

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
verified
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
Checkpoint revision
Runtime profile
zeroscope
Pipeline binding
zeroscope
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.component_pipelines:ZeroScopePipeline
Backend stage
in_tree_runtime
Runtime status
diffusers_text_to_video_ready
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 zeroscope
Package constraints 12
  • torch
  • torchvision
  • diffusers
  • transformers
  • accelerate
  • huggingface_hub
  • imageio
  • imageio-ffmpeg
  • numpy
  • opencv-python
  • safetensors
  • sentencepiece
Conda packages 3
  • python
  • pip
  • ffmpeg
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 zeroscope --check-local --json
cerspense/zeroscope_v2_576w
Revision
License
cc-by-nc-4.0
Gated
Private
cerspense/zeroscope_v2_XL
Revision
License
cc-by-nc-4.0
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 zeroscope \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/zeroscope \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
imageOptional
promptRequired

Artifact contract

Artifact kindFilename / path
generated_videozeroscope.mp4
05

Evidence & sources

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

Integration
integrated
Runner evidence
verified
Native demo evidence
Not recorded
Validation imports
torch, diffusers, transformers, imageio, cv2
Recipe provenance
worldfoundry/data/models/catalog/video/zeroscope.yaml