genmedia-labs
Official@genmedia-labs
genmedia-labs publishes MIT-licensed skills that route image, video, music, and avatar generation through the RunComfy CLI across dozens of hosted generative models.
Agent Skills by genmedia-labs
Showing 33 vetted skills indexed across 1 GitHub repositories.
genmedia-labsflux-2-klein
Generate images with Flux 2 Klein text-to-image models via the RunComfy CLI.
genmedia-labsvideo-extend
Extends existing video clips using Google Veo 3-1 extend-video endpoints via the RunComfy CLI.
genmedia-labshappyhorse-1-0
Generates text-to-video clips with HappyHorse 1.0 through the RunComfy CLI.
genmedia-labsace-step
Generate, inpaint, and outpaint music with ACE Step via the RunComfy CLI.
genmedia-labslipsync
Generates lip-synced videos from audio tracks and source media via the RunComfy CLI.
genmedia-labsgpt-image-edit
Edit images with OpenAI GPT Image 2 via the RunComfy CLI.
genmedia-labsnano-banana-edit
Edit images with Google Nano Banana 2 via the RunComfy CLI.
genmedia-labscontrolnet-pose
Generates pose-conditioned images and motion-transfer videos via the RunComfy CLI.
genmedia-labsflux-kontext
Edit images with Flux 1 Kontext Pro via the RunComfy CLI.
genmedia-labsimage-to-video
Routes image-to-video requests to HappyHorse, Wan 2.7, or Seedance models via the RunComfy CLI.
genmedia-labswan-2-7
Generate text-to-video clips with Wan 2.7 via the RunComfy CLI.
genmedia-labsnano-banana-2
Generate images with Google Nano Banana 2 text-to-image via the RunComfy CLI.
genmedia-labselevenlabs-music-generation
Generate songs and instrumental tracks from text prompts via the RunComfy CLI.
genmedia-labsimage-outpainting
Extends image canvases beyond original borders using RunComfy edit model endpoints.
genmedia-labskling-3-0
Generate multi-shot videos with synchronized audio via Kling 3.0 endpoints on RunComfy.
genmedia-labsai-image-generation
Generate and edit images via the RunComfy CLI across multiple AI image models.
genmedia-labsface-swap
Swap faces and characters in images and videos via the RunComfy CLI.
genmedia-labsimage-inpainting
Performs mask-driven image inpainting via the RunComfy CLI using Z-Image Turbo Inpainting.
genmedia-labsseedance-v2
Generate short-form video with ByteDance Seedance 2.0 Pro via the RunComfy CLI.
genmedia-labsseedance-2-5-reference-to-video
Generates reference-guided 1080p video with synchronized audio via the RunComfy CLI.
genmedia-labsai-avatar-video
Generate talking-head and lip-sync avatar videos via the RunComfy CLI.
genmedia-labsseedance-2-5-image-to-video
Animate a still image into a 4-30 second 720p video via the RunComfy CLI.
genmedia-labsai-music
Generate and edit AI music via the RunComfy CLI across ElevenLabs and ACE Step models.
genmedia-labsvideo-outpainting
Extend video canvas and change aspect ratio using RunComfy CLI and Wan 2-7 edit-video.
Frequently Asked Questions About genmedia-labs
FAQPage SchemaWhat tasks can I accomplish with genmedia-labs skills?▼
You can generate and edit images, produce text-to-video and image-to-video clips, extend or inpaint video, swap faces, lip-sync avatars to audio, relight stills, compose music with lyrics, and build Codex Pet spritesheets — all dispatched through the RunComfy CLI to models like Flux 2, GPT Image 2, Kling 3.0, Wan 2.7, Seedance, and ACE Step.
Who are these skills designed for?▼
Creative engineers, content producers, and developers who want terminal-driven access to hosted generative media models. Router skills (ai-image-generation, ai-video-generation, ai-music) suit users unsure which model fits, while Pro Pack skills serve users targeting a specific model like Flux Kontext or Seedance 2.0 Pro.
How do I install and run these skills?▼
Install the single runcomfy binary, authenticate with a RUNCOMFY_TOKEN, then invoke any model via `runcomfy run <vendor>/<model>/<endpoint>`. The runcomfy-cli skill documents schema discovery, polling, no-wait mode, and JSON output scripting; all sibling skills dispatch through this same binary.
Are genmedia-labs skills free and open source?▼
Yes, every skill in the manifest is released under the MIT license. The skills themselves are free; however, model execution on RunComfy is billed per use — for example ACE Step at $0.0002–0.0003 per second, ElevenLabs Music at $0.0083/s, and Seedance 2.5 image-to-video at $0.35/s.
What prerequisites or dependencies are required?▼
You need the local RunComfy CLI installed and a valid RUNCOMFY_TOKEN for authentication. No OPENAI_API_KEY or Codex Pro is required even for GPT Image 2 routes. The codex-pet skill additionally uses ImageMagick for spritesheet assembly, and Bash execution permission for `runcomfy *` commands.