wan-2-7

A skill for generating images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image model) on RunComfy, bundled with optimized prompting patterns for rapid iteration, in-image typography, and predictable framing.

A skill for generating and editing images with OpenAI GPT Image 2 on RunComfy, supporting text rendering, logos, multilingual typography, and intelligent routing to sibling models like Flux 2 when appropriate.

An intent-routing image editing skill for RunComfy that automatically selects the best model for each edit task, supporting batch edits, multilingual text rewriting, high-fidelity local edits, and mask-driven inpainting.

Generates cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references with up to 9 images, 3 videos, and 3 audio inputs with native lip-sync. Routes to the RunComfy CLI for 4 to 15 second video generation with synchronized audio.

A skill for editing images using Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with features like subject identity preservation, background swapping, and localized edits using spatial language.

Skill

Skill

Skill

A skill that animates still images by routing to the best image-to-video model on RunComfy, supporting HappyHorse 1.0 for general animations, Wan 2.7 for lip-sync with custom audio, and Seedance 2.0 Pro for multi-modal animation from image, reference video, and audio.

A smart video editing skill for RunComfy that routes user intent to the optimal model: Wan 2.7 Edit-Video for general restyling and background swaps, Kling 2.6 Pro for motion control transfers, or Lucy Edit for lightweight identity-stable restyling.