@doany-ai

image-inpainting performs mask-driven region edits via runcomfy cli, supporting both mask-based and prose-described inpainting workflows on z-image turbo infrastructure.

video-outpainting extends video canvas horizontally or vertically via runcomfy cli, routing requests to wan 2-7 edit-video or dedicated comfyui workflows depending on seam quality requirements.

video-inpainting enables object removal and region replacement across video frames via runcomfy cli, mapping user intents to prompt-driven edit endpoints with sensible defaults.

ace-step wraps stepfun-ai's music foundation model via runcomfy cli for generation, inpainting, and outpainting. supports tag-driven workflows across four endpoints at 0.0002-0.0003 per second of audio, capped at 4 minutes per call.

video-edit routes video editing requests to the appropriate runcomfy model based on user intent, supporting restyle, motion transfer, and identity-stable swaps via intent classification.

controlnet-pose routes pose-conditioned generation across kling and comfyui via runcomfy cli, but lacks procedural depth and actionable workflows for typical use cases.

video-extend chains or extends video clips using google veo 3-1 endpoints via the runcomfy cli, supporting narrative shot-by-shot generation from a seed prompt.

ai-avatar-video routes text and audio to multiple runcomfy avatar models (omnihuman, wan, happyhorse, seedance) with lip-sync, returning invoke commands and prompts for the selected path.

runcomfy-cli wraps a unified command-line interface for invoking any runcomfy model endpoint. installation and auth are one-time setup. the actual model invocation syntax and input contract are under-specified in this document.

relight adjusts still image lighting (direction, color temperature, intensity, mood) via runcomfy cli, routing to qwen edit 2509 or identity-preserving endpoints based on task complexity.

image-outpainting extends images beyond original boundaries using runcomfy endpoints, supporting prose-driven extension, reference matching, and brand-locked continuation.

happyhorse-1-0 provides text-to-video generation via runcomfy with native 1080p output and synchronized audio, but lacks procedural depth and failure guidance.

elevenlabs-music-generation wraps the runcomfy cli to produce multi-minute audio tracks from text prompts, but lacks actionable procedure, error handling, and concrete input/output contracts.

flux-kontext wraps black forest labs flux 1 kontext pro via runcomfy for single-image local edits. lacks procedural depth, executable steps, and failure mode documentation.

nano-banana-2 wraps google's flash-tier text-to-image model via runcomfy, optimized for rapid ideation and social thumbnails. lacks procedural substance and actionable step-by-step guidance.

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…

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1…

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio),…

Kling 3.0 video generation on RunComfy. Kling 3.0 (also called Kling V3.0) is Kuaishou Technology's third-generation multi-shot video model with native…

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait…

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…

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the…

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo,…

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…

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual…

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…

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 +…

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9…

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap…