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 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.
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.
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.
Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.
Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.
Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.
Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.
Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.
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.
A Claude Code skill for swapping faces in images and videos via RunComfy CLI, routing across multiple model endpoints including Wan 2-2 Animate, GPT Image 2 Edit, Flux Kontext, and Kling Motion Control based on use case.