flux-kontext
๐ฏSkillfrom doany-ai/skills
|A Claude Code skill for editing images with Black Forest Labs Flux 1 Kontext Pro on RunComfy, specializing in single-reference precise local edits with strong prompt control and consistent high-fidelity identity preservation.
Overview
Flux Kontext is a Claude Code skill for performing precise local image edits using Black Forest Labs' Flux 1 Kontext Pro model, hosted on the RunComfy Model API. It specializes in single-reference editing where you provide one source image and a declarative prompt describing a targeted change, such as swapping an object, modifying clothing, or replacing brand text. The skill preserves the source image's identity, pose, and framing with high fidelity while applying only the requested modification.
Key Features
- Single-reference precise local editing with a minimal schema (prompt + image URL), designed for targeted changes like "add an umbrella" or "replace brand text from ALPHA to AURA" without disturbing the rest of the image
- High-fidelity identity preservation that keeps faces, poses, clothing, and environmental context intact when editing specific regions, guided by preservation-first prompting patterns
- Seed-based reproducibility for generating variant series from the same source image, enabling controlled A/B testing of edits
- Built-in routing guidance that directs users to more appropriate models when the task calls for multi-image batch edits (Nano Banana Edit), multilingual text editing (GPT Image 2), or generation from scratch (Flux 2 Klein)
- Iterative editing workflow support, recommending sequential single-instruction passes for compound changes to prevent composition drift
Who is this for?
This skill is built for designers, brand managers, and product teams who need to make precise modifications to existing images, such as swapping product labels, adjusting accessories, or making targeted compositional changes. Developers building automated image editing pipelines through the RunComfy CLI will appreciate the minimal schema and deterministic seed support. It is especially useful for e-commerce teams doing product mockup iterations and marketing teams producing brand-asset variants from a single reference photo.
Same repository
doany-ai/skills(29 items)
Installation
npx vibeindex add doany-ai/skills --skill flux-kontextnpx skills add doany-ai/skills --skill flux-kontext~/.claude/skills/flux-kontext/SKILL.mdSKILL.md
More from this repository10
A Claude Code skill for image outpainting on RunComfy that extends images beyond their original canvas, supporting aspect ratio changes, uncropping, and canvas expansion by routing across Nano Banana 2 Edit, GPT Image 2 Edit, and FLUX Kontext Pro.
A Claude Code skill for pose-conditioned image and video generation on RunComfy, routing across Kling 2-6 Motion Control (video motion transfer), Wan 2-2 Animate (audio-driven character animation), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation).
A Claude Code skill that creates AI avatar and talking-head videos on RunComfy, intelligently routing across OmniHuman, Wan 2-7, HappyHorse, and Seedance models based on user intent such as UGC voiceover, virtual presenter, or lip-synced character.
A Claude Code skill for generating images with Google Nano Banana 2, a Gemini-family flash-tier text-to-image model hosted on RunComfy, optimized for rapid iteration, social thumbnails, and in-image typography rendering.
Extend a video's spatial canvas on RunComfy โ uncrop, change aspect ratio (e.g., 9:16 to 16:9), or add environment beyond the original frame while preserving the central action. Routes through Wan 2-7 edit-video and dedicated ComfyUI outpaint workflows.
A Claude Code skill that extends existing video clips on RunComfy using Google Veo 3-1's extend-video endpoints, continuing clips past their duration cap or chaining narrative shots while preserving consistent motion, lighting, and subject identity.
Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy โ studio-quality 44.1 kHz stereo audio from 5 seconds to 5 minutes with section-level control (Intro, Verse, Chorus, Bridge), multilingual vocals, and commercial-friendly output.
A Claude Code skill for generating and editing images with OpenAI GPT Image 2 (ChatGPT Images 2.0) hosted on RunComfy, with strengths in embedded text, logos, multilingual typography, and precise multi-element prompt following.
Animate any still image into video on RunComfy, routing to the best i2v model for each intent โ HappyHorse 1.0 for general animations with native audio, Wan 2.7 with audio_url for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image plus reference video and audio.
A Claude Code skill that acts as a smart router for video editing on RunComfy, automatically selecting the best model -- Wan 2.7 Edit-Video for general restyle, Kling 2.6 Pro for motion transfer, or Lucy Edit Restyle for lightweight outfit/background swaps.