Port or add a model to SD.Next using a phased integration flow: select the least-new-code path that follows SD.Next conventions, invoke port-pipeline when no upstream Diffusers implementation exists, then implement loader and routing updates and validate.
Assess and port custom model pipeline implementations to Diffusers: summarize scope and complexity and get user confirmation before implementation, preserve behavior, avoid new dependencies, and keep device/attention handling configurable. Always invoke…
Maintain and validate SD.Next model reference catalogs in data/reference*.json, including schema consistency, deduplication, link checks, and thumbnail alignment.
Scan modules/ui*.py, scripts/*.py, and ui/locale/locale_en.json to create missing hints, identify duplicates, flag incorrect hints without auto-updating them, and generate a categorized audit report.
Run a phased processing-workflow audit from UI submit bindings to backend execution: map workflow paths first, then validate parameter, type, and initialization correctness.
Run a phased scheduler audit from modules/sd_samplers_diffusers.py and scheduler UI definitions: verify class loadability first, then config validity against scheduler capabilities, then SamplerData correctness and UI option alignment.
Analyze an external model URL (typically Hugging Face) to determine implementation style and estimate SD.Next porting difficulty using the port-model workflow.
Run a phased scripts audit in scripts/*.py: validate Script overrides (init/title/show) first, then verify ui() output compatibility with run() or process() parameters.
Debug a broken SD.Next or Diffusers model integration. Use when a newly added or ported model fails to load, misdetects, crashes during prompt encoding or sampling, or produces incorrect outputs.
Create or edit code that is compliant with Hugging Face diffusers conventions, including models, pipelines, schedulers, tests, docs, and PR preparation targeting diffusers.
Run the SD.Next lint workflow in phased order: execute tools in sequence first, then apply minimal fixes, while ignoring findings explicitly marked by TODO comments in code.
Update wiki markdown docs for syntax correctness, readability, link integrity, heading hierarchy normalization, and code block language tagging. Use when a user asks to clean up markdown formatting and improve clarity while preserving technical meaning.
Read SD.Next GitHub issues with [Feature] in the title and produce a phased markdown report: short summary first, then status, then suggested next steps per issue.
Read SD.Next GitHub issues with the literal string [Issue] in the title and produce a phased markdown report: short summary first, then status, then suggested next steps per issue.