Menu
O SkillsMP coletou 18 skills de vladmandic/sdnext. Abra uma skill para revisar a origem e os detalhes.
Mostrando 18 de 18 skills coletadas.
Run a phased processing-workflow audit from UI submit bindings to backend execution: map workflow paths first, then validate parameter, type, and initialization correctness.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Maintain and validate SD.Next model reference catalogs in data/reference*.json, including schema consistency, deduplication, link checks, and thumbnail alignment.
Idioma do texto original: inglês
Audit SD.Next model integrations end-to-end: loaders, detect/routing, reference catalogs, and pipeline API contracts.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Analyze an external model URL (typically Hugging Face) to determine implementation style and estimate SD.Next porting difficulty using the port-model workflow.
Idioma do texto original: inglês
Audit SD.Next API route definitions and verify endpoint parameters plus request/response signatures against declared FastAPI contracts.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Audit Python-to-JavaScript UI bindings for Gradio _js calls, global window exposure, and ui/globals.d.ts registration.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Create or edit code that is compliant with Hugging Face diffusers conventions, including models, pipelines, schedulers, tests, docs, and PR preparation targeting diffusers.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Search the entire codebase for TODO markers and create a markdown document with proposed next steps for each.
Idioma do texto original: inglês