What does The Chosen One (iterative consistent-character extraction from a text prompt alone) cost per character, how was it measured, what failure modes do the authors list, and is there official code?
The Chosen One (arXiv 2311.10093v4, SIGGRAPH 2024) takes only a text prompt, generates a set of images, clusters their embeddings, optimises LoRA weights and two learned text tokens on the most cohesive cluster, and repeats until convergence. The authors report 1-2 iterations, about 13-26 minutes on an A100 (bfloat16), and list the cost as a limitation (about 20 minutes). Consistency is measured as pairwise CLIP image-embedding similarity across prompts and prompt similarity as CLIP score; the main result is a trade-off plot (Fig. 6) plus an AMT user study; the numbers are not in the HTML text. Stated failure modes: identity may not fully converge, a supporting character such as a pet is not kept consistent, spurious attributes can bind to the identity, one character at a time, and simplistic centred scenes. The author project page lists only an 'unofficial' code link. The catalogue already holds this paper as a source entry; this candidate adds the pinned v4 details.
Structured fields
{
"citations": [
{
"url": "https://arxiv.org/html/2311.10093v4",
"note": "candidate evidence excerpts"
},
{
"url": "https://omriavrahami.com/the-chosen-one/",
"note": "candidate evidence excerpts"
}
]
}Evidence claims
- [sourced_fact] The Chosen One (arXiv 2311.10093v4, SIGGRAPH 2024) takes only a text prompt, generates a set of images, clusters their embeddings, optimises LoRA weights and two learned text tokens on the most cohesive cluster, and repeats until convergence. The authors report 1-2 iterations, about 13-26 minutes on an A100 (bfloat16), and list the cost as a limitation (about 20 minutes). Consistency is measured as pairwise CLIP image-embedding similarity across prompts and prompt similarity as CLIP score; the main result is a trade-off plot (Fig. 6) plus an AMT user study; the numbers are not in the HTML text. Stated failure modes: identity may not fully converge, a supporting character such as a pet is not kept consistent, spurious attributes can bind to the identity, one character at a time, and simplistic centred scenes. The author project page lists only an 'unofficial' code link. The catalogue already holds this paper as a source entry; this candidate adds the pinned v4 details. · 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. |