AI Skills

Generate and edit images with OpenAI GPT Image 2 on RunComfy—best for embedded text, logos, and directive precision.

Extend image canvas, change aspect ratio, and fill in cropped areas using RunComfy's identity-preserving edit models.

Sub-second Flux 2 Klein image generation on RunComfy with pro prompting patterns.

One CLI, one auth, hundreds of RunComfy model endpoints for image, video, and creative AI tasks.

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro—multi-modal references, native lip-sync, 4–15s duration.

Generate videos with RunComfy's full model catalog—text-to-video, image-to-video, and video extend via one CLI.

Pose-conditioned image and video generation via RunComfy CLI—transfer motion, control character stance, or apply depth/canny conditioning.

Cinematic short-form video with multi-modal references and native lip-sync via ByteDance Seedance 2.0 Pro on RunComfy.

Generate and edit images with OpenAI GPT Image 2 on RunComfy—precise text rendering and layout control.

#1 ranked text-to-video model with native 1080p, synchronized audio, and multi-shot character consistency.

Generate custom Codex Pets from a single image via RunComfy—no Codex Pro required.

Sub-second Flux 2 Klein image generation on RunComfy—fast iteration with documented prompting patterns.

Smart router that picks the right image-to-video model on RunComfy based on user intent.

Pose-conditioned image and video generation via RunComfy CLI—transfer motion, control pose, or condition on skeleton/depth/canny.

Create AI avatar and talking-head videos by routing across OmniHuman, Wan 2-7, HappyHorse, and Seedance via RunComfy CLI.

Mask-driven image inpainting for object removal, watermark cleanup, and region replacement via RunComfy.

Smart router for video editing—picks the right model (Wan, Kling, or Lucy) based on your intent.

Edit images with GPT Image 2 on RunComfy—preserves identity, rewrites multilingual text, handles up to 10 reference images.

Change lighting direction, color temperature, and mood on still images via RunComfy's Qwen Edit Relight LoRA.

Smart router that picks the right image edit model (Nano Banana, GPT Image 2, Flux Kontext, or Z-Image) based on your intent.

Swap faces into videos or images via RunComfy—routes to the right model for your intent.

Extend or continue existing video clips using Google Veo 3-1 via RunComfy CLI.

Extend video canvas spatially—uncrop, change aspect ratio, add environment while preserving central action.

Flash-tier Google text-to-image on RunComfy—rapid drafts, social thumbnails, and predictable in-image typography.

Generate studio-quality songs and instrumentals from text descriptions using ElevenLabs Music on RunComfy.

Mask-driven image inpainting for object removal, watermark cleanup, and region replacement via RunComfy CLI.

Smart router for image edits—picks the right RunComfy model based on your intent.

Create talking-head and avatar videos by routing audio + images across RunComfy's OmniHuman, Wan, HappyHorse, and Seedance models.

Generate and edit images with 11+ AI models (FLUX 2, GPT Image 2, Seedream, Qwen, Wan) via RunComfy CLI.

Smart router for image-to-video on RunComfy — picks the right model (HappyHorse, Wan, or Seedance) based on user intent.