Kura

ComfyUI render workflow operations for Kura. Use when editing workflows/*.json, render run.yaml files, workflow_patches, promptsets, image comparison generation, ComfyUI endpoint behavior, or render result collection.

RunPod remote training lifecycle and billing safety for Kura. Use when working on kura run remote, runpod staging/upload/download/pull/stop/reconcile, Pod cleanup, max lease, notifications, GPU selection, Network Volumes, or RunPod docs/README updates.

Dataset preparation and validation for Kura training runs. Use when creating or editing datasets/, dataset.yaml, items.jsonl, captions, trigger words, paired/control datasets, dataset roles, or dataset validation behavior.

Local disk, WSL2, Docker, cache, cleanup, permission, and checkpoint safety workflow for Kura. Use before local Docker training, real model-download smoke tests, Docker image builds, RunPod downloads/pulls, cleanup, permission repair, or when the user mentions disk space, WSL, Docker storage, cache, checkpoints, root-owned files, cleanup, or a crash/reconnect incident.

Musubi Tuner backend guidance for Kura. Use when compiling or changing Musubi compile output, model bundle resolution, safetensors validation, LoRA output compatibility, dataset TOML generation, low-VRAM flags, batch/gradient accumulation, or Musubi Docker images.

Choosing training parameters and resource trade-offs for Kura LoRA runs. Use when proposing or reviewing run.yaml training parameters, judging VRAM fit from `kura run plan` Resources, reacting to CUDA OOM, choosing fp8/quantized artifacts, or deciding which memory-saving or quality trade-off to apply and what needs user approval.

AI-Toolkit backend and image workflow for Kura. Use when changing AI-Toolkit compile output, Docker image build/publish, Hugging Face cache behavior, or local/RunPod image contracts.

Pre-release or pre-commit quality gate for Kura. Use when preparing a commit, release, PR, or larger handoff; verifying tests, CLI help, docs, secrets, generated artifacts, workflows, and RunPod safety.

Core Kura repository operating rules. Use when changing Kura source code, run lifecycle behavior, workspace artifact handling, executor/backend boundaries, secrets handling, or any code that affects reproducible training/render runs.

Developer checklist for adding, updating, or verifying Kura's built-in Musubi Tuner architecture adapters and Docker image refs.

Reporting Kura experiment results for notes, Scrapbox, blog posts, X/Twitter, or comparison summaries. Use when summarizing training parameters, dataset size, generated comparison images, observed quality, caveats, and reproducible run IDs.

English technical replies for Kura-related issues, PRs, upstream questions, release notes, or support messages. Use when converting Japanese notes or repo findings into concise, careful English without leaking secrets.

Kura Textual monitor/watch TUI guidance. Use when changing kura monitor, kura run watch, src/kura/tui.py, src/kura/monitor.py, run summary loading, Textual widgets, path open/copy behavior, or read-only monitoring projections.

Publishing Kura-trained LoRA/model artifacts to Hugging Face or ModelScope. Use when preparing model cards, selecting safetensors outputs, checking metadata/license/sample images, or uploading releases without leaking secrets.

README and documentation synchronization for Kura. Use when updating README.md, docs/, examples, command examples, RunPod docs, release notes, or when CLI flags/behavior changed and documentation may be stale.