Use when Codex benchmarks or visualizes FlexCache strategies, updates ChituBench result.md, creates speed-quality trade-off plots, Pareto/frontier summaries, or visual contact sheets for cache acceleration methods such as TeaCache, MeanCache, PAB, BlockDance, Cubic, TaylorSeer, or similar.
Adapt a new image diffusion model into the ChituDiffusion repository. Use when the user gives a model name and wants Codex to pull or inspect the upstream reference code, run the original demo, quantify non-API-wrapper code, add a runtime adapter/stage-level API integration, wire attention backends and CFG/context parallelism, adapt FlexCache strategies, benchmark with ChituBench, update result.md, clean artifacts, and split categorized commits.