Routes your lighting change requests to Qwen Edit 2509's dedicated relight LoRA when you need surgical control over direction, color temperature, and intensity, with fallback to identity-preserving edit models when prose descriptions are enough. The prompting guide is genuinely useful: you specify light source type, color temp in Kelvin, angle, and intensity, then explicitly state what to preserve. Works well for product catalog relighting (studio to window light) and portrait mood shifts (overcast to golden hour). The model picker is honest about when to skip the relight LoRA and just use Nano Banana or FLUX for composite edits. No video support yet, despite ComfyUI workflows existing for it.

skills.sh installs
274K
GitHub stars
16
last updated
Aug 21, 2026

Install

$ npx -y skills add runcomfy-com/skills --skill relight --agent claude-code

Installs into .claude/skills of the current project.

Files

Relight

Change how a still is lit — direction, color temperature, intensity, mood — without redoing the shot. This skill routes to Qwen Edit 2509's dedicated relight LoRA when a purpose-built relighting endpoint matters, and to identity-preserving edit endpoints when prose lighting language is enough.

runcomfy.com · Qwen Edit relight · CLI docs

Powered by the RunComfy CLI

# 1. Install (see runcomfy-cli skill for details)
npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version

# 2. Sign in
runcomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>

# 3. Relight
runcomfy run qwen/qwen-edit-2509/lora/relight \
  --input '{"image": "...", "prompt": "..."}' \
  --output-dir ./out

CLI deep dive: runcomfy-cli skill.


Pick the right model

Sponsors

Details

Repository
github.com/runcomfy-com/skills
Categories
Backend & APIs, Design & UI/UX, CLI & Terminal, Generative Media
First seen
Jun 3, 2026

More from runcomfy-com/skills

All 28
1runcomfy-com avatargpt-image-editruncomfy-com/skillsEdit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the ski273.9Kskills.sh installs
2doany-ai avatarai-video-generationdoany-ai/skillsGenerate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan273.6Kskills.sh installs
3doany-ai avatarvideo-editdoany-ai/skillsEdit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edi273.4Kskills.sh installs
4scrapegraphai avatarjust-scrapescrapegraphai/just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, gr245Kskills.sh installs
5higgsfield-ai avatarhiggsfield-product-photoshoothiggsfield-ai/skillsGenerate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/213.9Kskills.sh installs
6inference-sh avataragent-toolsinference-sh/skillsRun AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, Om213.7Kskills.sh installs