flux-2-klein
๐ฏSkillfrom agentspace-so/runcomfy-agent-skills
|A RunComfy skill for generating images with Black Forest Labs' Flux 2 Klein, the distilled low-latency variant of Flux 2. Supports 9B and 4B model variants with sub-second inference for real-time art direction, rapid concepting, and multi-reference brand styling.
Overview
A RunComfy skill for generating images with Black Forest Labs' Flux 2 Klein, the distilled low-latency variant of Flux 2. Its defining strength is latency-first creative iteration: sub-second feedback that enables live art-direction sessions and rapid product visualization. Available in two variants (9B for higher detail when polishing, 4B for real-time speed), it uses a step-count strategy of 4-8 steps for fast iteration and approximately 25 steps for final polish. All calls route through the RunComfy CLI with async REST and no API key required.
Key Features
- Sub-second latency for real-time art-direction sessions and rapid iteration cycles
- Two model variants: 9B (higher detail at the end) and 4B (fastest real-time feedback)
- Step-count strategy: 4-8 steps for fast drafts, approximately 25 steps for polished output
- Multi-reference brand styling for consistent visual looks across generated images
- Declarative subject-first prompt grammar for precise control over generated content
Who is this for?
- Designers running live art-direction sessions who need real-time visual feedback as they refine prompts
- Product teams producing rapid visualization iterations where speed matters more than maximum resolution
- Developers building fast image generation into interactive applications that require sub-second response times
Same repository
agentspace-so/runcomfy-agent-skills(30 items)
Installation
npx vibeindex add agentspace-so/runcomfy-agent-skills --skill flux-2-kleinnpx skills add agentspace-so/runcomfy-agent-skills --skill flux-2-klein~/.claude/skills/flux-2-klein/SKILL.mdSKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that selects the best model based on the user's intent. Routes to Wan 2.7 Edit-Video for restyle and background swaps, Kling 2.6 Pro for precise motion transfer, or Lucy Edit for lightweight identity-stable restyle and outfit swaps.
A smart intent-routing skill for image-to-video generation on RunComfy that automatically selects the best model for the task. Routes to HappyHorse 1.0 I2V for general animations, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition from image, video, and audio references.
A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.
Edit images with Black Forest Labs' Flux 1 Kontext Pro on RunComfy, specializing in single-reference precise local edits with high-fidelity source preservation. Ideal for targeted changes like adding objects or modifying details while keeping the rest of the image unchanged.
A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.
Provides Kling 3.0 video generation on RunComfy, covering all six endpoints across three quality tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video) for Kuaishou's third-generation cinematic video model with native synchronized audio.
Generates custom Codex Pets for OpenAI Codex using RunComfy's GPT Image 2 edit endpoint. Turns a single reference image into a Codex-compatible spritesheet (1536x1872, 9 animation states) and pet.json manifest with just one API call, requiring only a RUNCOMFY_TOKEN โ no Codex Pro or OPENAI_API_KEY needed.
A Claude Code skill for generating AI videos through RunComfy CLI, supporting models like HappyHorse, Wan 2-7, Seedance, Kling, and Veo for text-to-video, image-to-video, and video-extend with automatic model selection.
A Claude Code skill that generates and edits images through RunComfy CLI, supporting 11+ AI models including FLUX 2, GPT Image 2, and Google Nano Banana with automatic model selection for text-to-image and image-to-image workflows.
The foundation skill for the RunComfy platform, providing a single CLI to install, authenticate, and invoke hundreds of model endpoints including image generation, video, face-swap, lip-sync, and LoRA training.