I want the same character to look the same across the panels of a storyboard made with an image model: what does 'consistent' mean in the primary research, and which method family should I try first?

The papers and benchmark do not share one definition of 'consistent character'. StoryDiffusion and ConsiStory share attention across images generated together (whole subject incl. attire, no reference photo); The Chosen One iteratively extracts an identity from a text prompt alone; PhotoMaker and InstantID encode a person's face from photo(s); ViStoryBench measures reference-matched characters per shot with detection plus face/CLIP embeddings. Each source names limits: single person only (PhotoMaker), largest face only (InstantID), no consistent supporting characters (The Chosen One), same style only (ConsiStory), and no background-reference evaluation (ViStoryBench). In ViStoryBench's full-set Table 2 a pasted reference image has higher CIDS (cross 0.929, self 0.984) than any generator row, so similarity must be read together with prompt alignment. No inspected source documents a named storyboard or previs production job; storyboard use is a hypothesis built on the authors' own comic/story demos. Curator correction 2026-10-23 (discovery audit record C3-B681-01; sources re-fetched 2026-10-23, excerpts re-located by curator GET): Problem. C3-B227-G69-06 (and the Table 2 sentence in C3-B227-G69-01) present the copy-paste baseline CIDS 0.929 cross / 0.984 self as a fixed reference. Correction type: (c) missing an important limitation / (e) changed since the paper. Conditions. Applies when you re-run the ViStoryBench CIDS evaluator and compare to the paper's copy-paste row. Method. The evaluator README states that, for characters with a single reference image, the current code computes the copy-paste score with a mirrored reference image, and that the paper and project-homepage numbers pre-date that fix. Rerun the baseline yourself with the same code version as your model rows instead of importing 0.929/0.984. Limitations. The README says only 'slightly different'; the size of the shift was not measured here. Version and date. README at pinned commit b44ec91 (identical bytes at main, fetched 2026-10-23). Curator qualifications: No shared definition of 'consistent character': batch attention sharing (whole subject incl. attire), text-only identity extraction, and reference-face encoders measure different things. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://arxiv.org/html/2505.24862v5",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2405.01434v1",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2402.03286v3",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2311.10093v4",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2312.04461v1",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://arxiv.org/html/2401.07519v2",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/instantX-research/InstantID/tree/2145b67f9607da6234702063692330185f374486",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://raw.githubusercontent.com/ViStoryBench/vistorybench/b44ec9108668cc2bcc8c5280886b235e9fb8bea9/README.md",
      "note": "correction source (record C3-B681-01): README note after the evaluation CLI options; same note"
    }
  ]
}