articleactivePreproduction and storyboards Video generation 3D and worlds Evaluation and media provenance

Which VBench-2.0 dimensions can I run on my own clips (for example previs shots), what do they need, and which only work on the standard prompt suite?

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-24 · art_01M5NNH8R23FWG1S6G06H3HXK6

Evidence: review revision unknown · inspection source_inspected · execution not_run · review unreviewed · origin research_agent

At the pinned repo commit, only five of the 18 dimensions accept custom videos: Human Anatomy, Human Identity, Human Clothes, Diversity (needs 20 clips per prompt) and Multi-View Consistency. The other 13 (including Camera Motion, Instance Preservation, Motion Rationality and all Controllability and Physics state-change dimensions) assert-fail on custom input and need the standard prompt suite, which means sampling the model under test on fixed prompts (3,860 videos for a full run by my count). Requirements are heavy (CUDA 11.8, flash-attention build, several third-party weights, some from Google Drive/Dropbox). Curator qualifications: All 10 excerpts located; five custom-input dimensions per the pinned repo. README/sampled_videos/paper model-count conflict kept. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

Structured fields

{
  "citations": [
    {
      "url": "https://github.com/Vchitect/VBench/tree/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Vchitect/VBench/blob/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0/README.md",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Vchitect/VBench/tree/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0/prompts",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Vchitect/VBench/tree/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0/pretrained",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2503.21755v2",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Vchitect/VBench/blob/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0/sampled_videos/README.md",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/Vchitect/VBench/blob/fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490/VBench-2.0/README-FAQ.md",
      "note": "candidate evidence excerpts"
    }
  ]
}

Evidence claims

[sourced_fact] At the pinned repo commit, only five of the 18 dimensions accept custom videos: Human Anatomy, Human Identity, Human Clothes, Diversity (needs 20 clips per prompt) and Multi-View Consistency. The other 13 (including Camera Motion, Instance Preservation, Motion Rationality and all Controllability and Physics state-change dimensions) assert-fail on custom input and need the standard prompt suite, which means sampling the model under test on fixed prompts (3,860 videos for a full run by my count). Requirements are heavy (CUDA 11.8, flash-attention build, several third-party weights, some from Google Drive/Dropbox). · locator: candidate evidence excerpts source

Rights

component	license	hosting	redistribution	modification	training	Evidence and notes
documentation	unknown	permitted	permitted	unknown	unknown	Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes