Metraipolis › archive › dc_af7289bf50ab

Well-Typed ComfyUI Cannot Go Wrong: Gradual Refinement Types for Generative-AI Workflow Graphs — arXiv:2610.37673

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.37673
License (as archived)
CC0-1.0
Archived
2026-11-01T02:29:06.396Z
SHA-256 of the archived text
2ad3996a2b81b2afbb9ef346975eae806a7b9c6999e9c677777e7e3f67e7b4e4
Stable URL of this page
https://metraipolis.com/documento/dc_af7289bf50ab

How to cite

Well-Typed ComfyUI Cannot Go Wrong: Gradual Refinement Types for Generative-AI Workflow Graphs — arXiv:2610.37673 — arXiv (en), https://arxiv.org/abs/2610.37673 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af7289bf50ab (Metraipolis archive dc_af7289bf50ab, sha256 2ad3996a2b81b2afbb9ef346975eae806a7b9c6999e9c677777e7e3f67e7b4e4)
BibTeX
@misc{dcaf7289bf50ab,
  title = {Well-Typed ComfyUI Cannot Go Wrong: Gradual Refinement Types for Generative-AI Workflow Graphs — arXiv:2610.37673},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.37673},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af7289bf50ab; sha256 2ad3996a2b81b2afbb9ef346975eae806a7b9c6999e9c677777e7e3f67e7b4e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37673. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative-AI workflows are programs assembled from independently developed models and operators. Their correctness depends on relationships among model families, tensor geometry, control modalities, and quantization levels. In ComfyUI, these relationships can be violated even when every connection is accepted by its validator, causing expensive runtime crashes or silent failures. To measure how often such semantic composition failures occur, we classify all 8,766 issues and 1,368 discussion threads of ComfyUI's GitHub repository with an LLM, checked for cross-model agreement. They account for 8\% of issue reports and 21\% of issue-tracker runtime failures, and 32\% of them are silent. Because execution cannot reliably reveal those failures, we present ComfyTy, a gradual refinement type system that checks component compatibility before execution as a compositional property of workflow graphs. Each node declares a reusable schema that states which model families, sizes, modalities, and quantizations it accepts and produces. Wiring nodes together combines their schemas into constraints, which ComfyTy solves to find and report incompatibilities. To evaluate ComfyTy, we first inject faults into official ComfyUI workflows and execute every resulting graph. ComfyTy detects 66.4\% of the confirmed injected faults, all of which ComfyUI's own validator admits. On real workflows across more model families, it raises no false alarm on 765 known-good workflows and detects 67\% of 108 failures rebuilt from user reports. Finally, in a user study with 10 participants, its diagnostics raise fault-localization accuracy on faulty workflows from 35.0\% to 87.5\% and repair accuracy from 30.0\% to 62.5\%.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Programming Languages (cs.PL) ; Multimedia (cs.MM); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.37673 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:58.501Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).