Model strengths by job: which model measured best for stills, text, product, restyle, identity restage, music, voice and video
A short dated reference of measured comparisons (bake-offs, blind reviews, ArcFace identity scores, OCR) naming the strongest and weakest models per job, with evidence paths. Knowledge for choosing a model, not a fixed recipe.
Discover · Wavemaker catalog
When to use it
- A short dated reference of measured comparisons (bake-offs, blind reviews, ArcFace identity scores, OCR) naming the strongest and weakest models per job, with evidence paths. Knowledge for choosing a model, not a fixed recipe.
What you get
- A creative method with its instructions and supporting source files.
Setup and requirements
- Follow the included guide to bind your inputs and select the appropriate runtime.
Things to know
- Dated October 10, 2026; a model or route that changes needs a new measurement.
- Jobs marked not measured have no head-to-head evidence; reputation is not a measurement.
- Search ranking is not quality: check the chosen model can run (generation.prepare runtime_compatibility, providers.routes) and review the actual output.
Source licenses and model terms continue to apply. Check runtime availability before generation.
Download source · Learn how to reuse resources