How does ConsiStory keep one subject consistent across prompts without training, how was that measured, what are its stated failure modes and costs, and can the official code be used commercially?

ConsiStory (arXiv 2402.03286v3, SIGGRAPH 2024 TOG) shares internal activations between the images of a set so that a subject stays consistent without any optimisation step; the first two prompts act as anchors (paper: two anchor images, 0.5 dropout). The authors evaluate 100 image sets with DreamSim (background removed) and CLIP and a 3,000-response two-alternative user study; the quantitative headline is a plot, not text. Timing: 32 s on an H100 for two anchors plus one new image, about 25x faster than The Chosen One (their estimate of 13 min). Stated limits: it relies on cross-attention localisation (failures below 5% in their observation, fixable by changing the seed), images in a set must share one style, and SDXL biases carry over. The official NVlabs code is under the NVIDIA License, which permits only non-commercial use and only with NVIDIA Processors. Curator qualifications: ConsiStory shares activations within a set with anchor images; authors evaluate 100 sets with DreamSim/CLIP. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary. Limitations: [component_reuse_restriction] NVIDIA non-commercial licence (producer). 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/2402.03286v3",
      "note": "candidate evidence excerpts"
    },
    {
      "url": "https://github.com/NVlabs/consistory/tree/8158d411980d9d97140a170607a314039bdadd6f",
      "note": "candidate evidence excerpts"
    }
  ]
}