Menu
SkillsMP has collected 18 skills from vladmandic/sdnext. Open a skill to review its source and details.
Showing 18 of 18 collected skills.
Run a phased processing-workflow audit from UI submit bindings to backend execution: map workflow paths first, then validate parameter, type, and initialization correctness.
Port or add a model to SD.Next using a phased integration flow: select the least-new-code path that follows SD.Next conventions, then implement loader and routing updates, then validate.
Maintain and validate SD.Next model reference catalogs in data/reference*.json, including schema consistency, deduplication, link checks, and thumbnail alignment.
Audit SD.Next model integrations end-to-end: loaders, detect/routing, reference catalogs, and pipeline API contracts.
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.
Audit SD.Next model-loading code for cache_dir routing on from_pretrained/from_single_file calls and verify diffusers vs HF cache path selection.
Analyze an external model URL (typically Hugging Face) to determine implementation style and estimate SD.Next porting difficulty using the port-model workflow.
Audit SD.Next API route definitions and verify endpoint parameters plus request/response signatures against declared FastAPI contracts.
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.
Audit Python-to-JavaScript UI bindings for Gradio _js calls, global window exposure, and ui/globals.d.ts registration.
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.
Port custom model pipeline implementations to Diffusers using phased priorities: preserve behavior first, avoid new dependencies second, and keep device/attention handling configurable throughout. Use when migrating custom or non-Diffusers pipeline code into…
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.
Search the entire codebase for TODO markers and create a markdown document with proposed next steps for each.