WorldFoundry
English中文

VideoCrafter1 T2V

VideoCrafter1 T2V

VideoCrafter1 T2V from Tencent AI Lab: text-to-video and video-generation; Runner parity pending.

Edit this pageGitHubMarkdown

VideoCrafter1 T2V is the text-to-video member of the VideoCrafter1 release, generating clips up to 1024x576 from a prompt. The in-tree infer-only runtime wraps the official text-to-video 1024 path with local checkpoint, fps, frame count, and seed controls.

No official teaser or method figure is checked into this docs tree.

The recorded paper is arXiv 2401.09047.

Project page: ailab-cvc.github.io/videocrafter2. Code: VideoCrafter/VideoCrafter.

Build your run

Pipeline
VideoCrafter1T2VPipelineworldfoundry.pipelines.videocrafter.pipeline_videocrafter1_t2v
TaskInteractive Video interactive-video
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
Runnerworldfoundry.pipeline
Loadingfrom_pretrained
Invocationnative_or_standard_invocation
worldfoundry-eval run \
  videocrafter1-t2v \
  --pipeline.task-profile interactive-video \
  --json

What it is for

Pick videocrafter1-t2v when you want this family's text-to-video line in WorldFoundry: a prompt in, a generated clip out. Use it as the catalog T2V start rather than an editor or a world-model stepper.

U-Net latent video diffusion at up to 1024x576 (per the upstream release). Checkpoint provenance is tracked on the family entry; training and download scripts are excluded. It is published by Tencent AI Lab.

Catalog tasks include text-to-video and video-generation. Catalog aliases include videocrafter1_t2v. Documented modalities: text in, video out.

Recorded evaluation entry points include EvalCrafter (Companion benchmark of the VideoCrafter effort).

Not VideoCrafter and VideoCrafter2 T2V. Score on EvalCrafter.

Runtime contract

Optional prompt, frames, fps, height, and width; artifacts generated_video and videocrafter1-t2v.mp4.

CLI task profiles: interactive-video. WorldFoundry binds VideoCrafter1T2VPipeline.

Family status: Runner parity pending.

Runner parity is pending. Prefer VideoCrafter2 T2V for better visual quality from the same family, or the DiT entries for current-generation quality.

Checkpoint provenance is tracked on the top-level videocrafter catalog entry to avoid duplicate HF repo aliases.

Running in WorldFoundry

Launch worldfoundry-eval run videocrafter1-t2v --pipeline.task-profile interactive-video to sample the clip. The command builder above switches --pipeline.task-profile among recorded tasks and still emits worldfoundry-eval run.

It runs in the unified environment worldfoundry-unified-cu128 (Python 3.11, CUDA 12.8).

Recorded weight repositories include VideoCrafter/Text2Video-1024. Prepare the environment and check local assets with bash scripts/inference/prepare_model_infer.sh videocrafter1-t2v. Add --download to fetch missing public checkpoints.

Status: Runner parity pending.