doany-ai avatar

Flux Kontext

Wraps Black Forest Labs' Flux 1 Kontext Pro through RunComfy's CLI for single-image precise local edits. You feed it one source image and a declarative prompt like "she's now holding an orange umbrella" and it makes the change while preserving everything else. The skill bakes in the model's documented prompting patterns (preservation-first instructions, single-instruction edits) so you get cleaner results than raw API calls. Good for brand asset swaps, product mockups, or iterating on one hero image. For batch edits across multiple images or multilingual text changes, it routes you to Nano Banana Edit or GPT Image 2 instead. Requires the RunComfy CLI and an account.

skills.sh installs
274.1K
GitHub stars
5
last updated
Aug 21, 2026

Install

$ npx -y skills add doany-ai/skills --skill flux-kontext --agent claude-code

Installs into .claude/skills of the current project.

Files

Flux Kontext Pro — Pro Pack on RunComfy

runcomfy.com · Model page · GitHub

Black Forest Labs' Flux 1 Kontext Pro — single-reference precise local image edit — hosted on the RunComfy Model API. Strong prompt control, consistent outputs, high fidelity.

npx skills add agentspace-so/runcomfy-skills --skill flux-kontext -g

When to pick this model (vs siblings)

You wantUse
Single-image precise local edit ("she's now holding X")Flux Kontext
High-fidelity preservation of source identityFlux Kontext
Batch edits across 1–20 imagesNano Banana Edit
Edit multilingual / embedded text in imageGPT Image 2 edit
Generate from scratch, no source imageFlux 2 Klein

If the user said "Flux Kontext" / "kontext" / "BFL Kontext" explicitly, route here regardless.

Prerequisites

Sponsors

Details

Repository
github.com/doany-ai/skills
Categories
AI & Agent Building, Python, CLI & Terminal, Generative Media
First seen
Jun 3, 2026

More from doany-ai/skills

All 29
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
2runcomfy-com avatarhappyhorse-1-0runcomfy-com/skillsGenerate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass s273.9Kskills.sh installs
3runcomfy-com avatarvideo-extendruncomfy-com/skillsExtend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick273.8Kskills.sh installs
4runcomfy-com avatarflux-kontextruncomfy-com/skillsEdit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so 273.8Kskills.sh installs
5doany-ai avatarvideo-inpaintingdoany-ai/skillsRegion edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a 273.4Kskills.sh installs
6doany-ai avatarwan-2-7doany-ai/skillsGenerate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-273.3Kskills.sh installs