AI Skills

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

Generate AI music via RunComfy CLI—route to ElevenLabs premium vocals or cheap open-weights ACE Step, plus audio editing.

Tag-driven music generation, inpainting, and outpainting with StepFun-AI's ACE Step model on RunComfy.

Edit images with OpenAI GPT Image 2 on RunComfy—preserves identity and handles multilingual text better than naive prompting.

Sync a face's mouth to audio using Sync Labs, OmniHuman, Kling, or Creatify via RunComfy.

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

Extend existing video clips with Google Veo 3-1, chaining narrative shots with consistent motion and identity.

Remove objects, watermarks, and unwanted regions across video frames using prompt-driven AI editing.

One CLI, one auth, hundreds of model endpoints—run any RunComfy model from the command line.

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

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

Sync audio to a face's mouth across OmniHuman, Sync Labs, Kling, and Creatify via RunComfy CLI.

Kuaishou's Kling 3.0 cinematic video generation—text-to-video or image-to-video across Standard, Pro, and 4K tiers.

Precise local image edits with Flux 1 Kontext Pro on RunComfy—single-reference, high-fidelity, strong prompt control.

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

Tag-driven music generation, inpainting, and outpainting with ACE Step on RunComfy—$0.0002–0.0003/s.

Generate text-to-video with Wan 2.7's multi-reference conditioning and audio-driven lip-sync on RunComfy.

Precise local image edits with Flux 1 Kontext Pro on RunComfy—single-reference, high-fidelity edits via CLI.

Generate AI videos via RunComfy CLI—text-to-video, image-to-video, and video-extend across HappyHorse, Kling, Seedance, Wan, Veo, and more.

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

Remove objects, watermarks, and unwanted regions across video frames using prompt-driven AI editing.

Generate cinematic video with Kling 3.0 on RunComfy—text-to-video or image-to-video across Standard, Pro, and 4K tiers.

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

Generate text-to-video with Wan 2.7's audio-driven lip-sync and multi-reference conditioning on RunComfy.

Edit images with Google Nano Banana 2 on RunComfy—batch up to 20 images while preserving subject identity.

Generate AI music via RunComfy CLI—route to ElevenLabs premium vocals or ACE Step cheap open-weights, plus audio-inpaint and outpaint.

Manage shadcn/ui components, projects, and design systems with CLI-driven component addition and composition.

Search, scrape, crawl, and extract structured data from web pages via ScrapeGraph AI CLI.

Identify Azure cost savings from usage data and orphaned resources.

Build, debug, and publish Tampermonkey and ScriptCat userscripts with proper metadata, permissions, and runtime selection.