skills.rest
genmedia-labs
genmedia-labsOFFICIAL
Explore all skills by this author →
GitHub

flux-kontext

Edit images with Flux 1 Kontext Pro via the RunComfy CLI.

12|2|Updated Aug 12, 2026
Search Tags:#prompt engineering#cli#image editing#image-to-image#runcomfy#black forest labs#flux kontext
One-click install
npx skills add https://github.com/genmedia-labs/skills --skill flux-kontext-genmedia-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: flux-kontext
Source: https://github.com/genmedia-labs/skills/tree/main/flux-kontext
Command: npx skills add https://github.com/genmedia-labs/skills --skill flux-kontext-genmedia-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Performing precise local edits on a single source image—like swapping label text or adding an object—without disturbing the rest of the composition is hard with generic image models. This Skill routes those edits to Black Forest Labs' Flux 1 Kontext Pro on the RunComfy Model API with documented prompting patterns that reduce drift. ## Core Features & Use Cases - Single-reference local edits: Pass one image URL plus a declarative prompt to make targeted changes while preserving identity, pose, and framing. - Prompting guidance: Built-in patterns (preservation-first phrasing, single-instruction edits, seed-based variant series) that produce stronger results than naive prompting. - Model routing advice: Clear criteria for when to use Nano Banana Edit, GPT Image 2 edit, or Flux 2 Klein instead. - Use Case: A brand designer needs to replace the text on a product bottle label from "ALPHA" to "AURA" while keeping the bottle, lighting, and table unchanged—one CLI call with a preservation-led prompt handles it. ## Quick Start Ask the agent to edit an image with Flux Kontext, for example: "Use Flux Kontext to add an orange umbrella to this person's left hand while keeping everything else unchanged."

Frequently Asked Questions about flux-kontext

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I edit an image with Flux Kontext on RunComfy?▼

Install the RunComfy CLI with npm i -g @runcomfy/cli, log in, then run runcomfy run blackforestlabs/flux-1-kontext/pro/edit with a JSON input containing your prompt and a publicly fetchable image URL. Results download to your specified output directory.

Flux Kontext vs Nano Banana Edit for image editing?▼

Flux Kontext is designed for single-image precise local edits with strong identity preservation. Nano Banana Edit handles batch edits across 1-20 images and multi-image references, so route multi-image workflows there instead.

What prompts work best with Flux 1 Kontext Pro?▼

Use one declarative instruction in imperative mood, leading with a preservation statement like "Keep the face, pose, and clothing unchanged" followed by the single change. Compound prompts with multiple edits tend to drift, so split them into sequential passes.

Can Flux Kontext edit multiple images at once?▼

No, the schema accepts only a single source image URL plus a prompt. For multi-image fanout or batch edits across up to 20 images, the documentation directs you to Nano Banana Edit instead.

Why does Flux Kontext drift on compound edit prompts?▼

Kontext is tuned for single declarative instructions, so prompts combining several changes cause inconsistent results. Split the work into sequential single-instruction passes, such as changing the background first and clothing second.

How do I authenticate the RunComfy CLI in CI environments?▼

Set the RUNCOMFY_TOKEN environment variable instead of running runcomfy login, which uses an interactive browser device-code flow. The token file is stored at ~/.config/runcomfy/token.json with owner-only permissions for local use.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

gpt-image-2

Generate and edit images with embedded text using text prompts and reference images.

Official
Advanced
iterationlayeriterationlayer
2

remove-background-and-generate-product-card

Remove photo backgrounds and generate branded product listing card PNGs.

Official
Intermediate
brainworkupbrainworkup
1

generate-image

Generates and edits AI images from textual prompts using OpenRouter API.

Community
Intermediate
agentspace-soagentspace-so
31

image-edit

Route image editing requests to the appropriate RunComfy edit model.

Official
Intermediate