@runcomfy-com

lipsync syncs audio to facial animation across multiple backends (omnihuman, sync labs, kling, creatify) via the runcomfy cli, selecting the appropriate model based on user intent.

ai-avatar-video routes across multiple RunComfy audio-driven avatar models (OmniHuman, Wan, HappyHorse, Seedance v2) to generate talking-head and lip-sync videos, with model selection based on user intent.

ai-image-generation routes text-to-image and image-to-image requests across 11+ models via runcomfy cli, selecting appropriate models and providing prompt patterns for each invocation.

ai-video-generation routes text-to-video, image-to-video, and video-extend requests through runcomfy cli, selecting appropriate models and supplying prompt patterns for each.

video-edit routes user requests to appropriate runcomfy models (wan 2.7, kling motion-control, lucy restyle) based on detected intent for video transformation tasks.

ai-music routes generation requests to appropriate models in the runcomfy catalog, covering vocal songs, instrumentals, and multilingual covers via CLI. explicit routing logic and documented prompting patterns but procedure remains incomplete.

ace-step provides tag-driven music generation and inpainting via runcomfy cli, leveraging stepfun-ai's open-weights model. incomplete documentation and unclear procedures limit practical adoption.

elevenlabs-music-generation enables generation of full songs and instrumental tracks via runcomfy cli, supporting 5-second to 5-minute outputs at 44.1 khz stereo with section-level control.

seedance-v2 wraps ByteDance's multimodal video generator on RunComfy, accepting character images and reference audio to produce lip-synced short-form video. the skill lacks procedural depth and error handling.

relight adjusts lighting properties on static images by routing requests to specialized endpoints, supporting both dedicated LoRA models and identity-preserving edits via runcomfy cli.

gpt-image-2 generates and edits images via runcomfy's hosted openai model, excelling at multi-element prompts and embedded text. no local key required, async rest api.

nano-banana-2 wraps google's flash-tier text-to-image model on runcomfy for rapid social media and ui mockup generation with strong typography handling, but lacks concrete procedural steps and failure recovery paths.

kling-3-0 wraps six runcomfy video generation endpoints (text-to-video and image-to-video across standard, pro, and 4k tiers) for cinematic multi-shot video synthesis with synchronized audio and character consistency.

controlnet-pose routes pose-conditioned image and video generation across kling motion control endpoints via the runcomfy cli, with optional comfyui workflow integration for advanced rigging.

gpt-image-edit wraps openai's image edit endpoint on runcomfy for targeted image modifications. covers identity preservation and multilingual text rewriting. installation command provided but lacks complete operational guidance.

runcomfy-cli wraps a unified command-line interface for accessing runcomfy's text-to-image, video, and other generative endpoints after single authentication, but lacks actionable procedures and failure handling.

video-outpainting extends video canvas dimensions via Wan 2-7 or ComfyUI workflows, supporting aspect ratio changes and spatial uncropping while maintaining subject focus.

happyhorse-1-0 is a text-to-video model on runcomfy ranked #1 on artificial analysis video arena, supporting native 1080p output with synchronized audio and character consistency, but the documentation is incomplete and lacks actionable procedure.

flux-kontext wraps black forest labs' flux 1 kontext pro for precise local image edits via runcomfy api, with prompt control and high fidelity output. lacks procedural depth and error handling.

nano-banana-edit exposes google's nano banana 2 image-to-image model via runcomfy api, supporting batch operations on up to 20 images per request.

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints —…

Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio…

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven…

Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit…

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask,…

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into…

Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so…

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a…

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation +…

coll_image-to-video — an installable skill for AI agents, published by runcomfy-com/skills.

coll_video-edit — an installable skill for AI agents, published by runcomfy-com/skills.

coll_ai-image-generation — an installable skill for AI agents, published by runcomfy-com/skills.

coll_ai-music — an installable skill for AI agents, published by runcomfy-com/skills.

coll_ai-video-generation — an installable skill for AI agents, published by runcomfy-com/skills.

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks…