@kalvinrv

happyhorse-1-0 wraps the runcomfy cli for text-to-video generation with native 1080p output, in-pass synchronized audio, and multi-shot character consistency across six prompt languages.

mask-driven image inpainting on runcomfy via cli, routing to z-image turbo for precise region edits (object removal, watermark cleanup) and description-based models when masks unavailable. covers strength tuning, prompting heuristics, and fallback workflows.

relight alters still image lighting via runcomfy cli, routing to qwen edit 2509 relight lora for dedicated work or falling back to broader edit endpoints for composite passes. covers direction, color temperature, intensity, and mood shifts while preserving subject identity.

flux-2-klein wraps black forest labs' distilled flux 2 on runcomfy for sub-second image generation. covers model selection (4b vs 9b), step-count strategy, multi-reference styling, and documented prompting patterns that improve output over naive requests.

ai-avatar-video-runcomfy routes text or audio to five lip-sync and talking-head models (OmniHuman, Wan 2-7, HappyHorse, Seedance v2, Wan 2-2 Animate) via the runcomfy CLI, picking the right endpoint for UGC, presenter, dubbed, or cinematic use cases.

image-outpainting-runcomfy extends image canvas via the runcomfy cli, routing across nano banana 2 edit, gpt image 2 edit, flux kontext pro, and brand endpoints based on input type (prose-driven, reference-style, or brand-locked). includes aspect ratio changes, uncropping, and environment fill.

seedance-v2 generates cinematic short-form video via runcomfy cli with multi-modal conditioning (up to 9 images, 3 videos, 3 audio refs) and native in-pass lip-sync, tuned for spokesperson ads and branded narratives.

lipsync routes across four vendors (sync labs, omnihuman, kling, creatify) to match audio to mouth motion. handles portrait-to-avatar, video-to-dubbed-video, and script-to-synced-speech via runcomfy cli with explicit model selection logic.

wan-2-7 generates text-to-video on runcomfy with audio-driven lip-sync, multi-reference conditioning, and smooth motion physics. routes competing requests to happyhorse, seedance, kling, or ltx based on user intent.

flux kontext routes precise single-image edits to black forest labs' kontext pro model via runcomfy cli, with documented prompting patterns, routing logic to sibling models, and exit-code reference for error handling.

pose-conditioned video and image generation on runcomfy, routing across kling motion control, wan 2-2 animate, and z-image controlnet lora based on input type and aesthetic requirements.

face-swap-runcomfy routes video and still-image face swaps across five runcomfy models (wan 2-2 animate, kling motion control, nano banana edit, gpt image 2 edit, flux kontext) by intent, with explicit consent warnings and per-route decision logic.

codex-pet generates custom pixel-art animated desktop companions for openai codex via runcomfy's gpt image 2 api and imagemagick micro-transforms. outputs a codex-compatible spritesheet.webp and pet.json manifest without requiring codex pro or openai api credentials.

runcomfy video generation skill routes across a deep catalog of t2v, i2v, and extend endpoints (happyhorse, kling, seedance, veo, wan, hailuo, dreamina), each with pick/avoid guidance and prompting patterns. lacks procedural rigor on error handling and fallback logic.

See what your AI dev agent is doing, from anywhere — free, no-signup live dev workspace for AI agent development. The dev agent keeps writing — logs, generat...

Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, n...

GPT Image 2 on RunComfy. GPT Image 2 (OpenAI ChatGPT Images 2.0) is the strongest text-rendering image model available — embedded text, logos, signage, multi...

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...

Video edit on RunComfy. This video edit skill transforms an existing video clip — restyle, background swap, outfit swap, motion transfer, color grade, or any...

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

Nano Banana 2 on RunComfy. Nano Banana 2 is Google's flash-tier text-to-image model in the Gemini family — fast iteration, predictable framing, in-image typo...

Image-to-video generation on RunComfy. This image-to-video skill turns any still image into a short video clip via the RunComfy Model API. The image-to-video...

Image edit on RunComfy. This image edit skill transforms an existing image — background swap, object removal, in-image text rewrite, mask- driven region repl...

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 synch...

AI image generation on RunComfy. This RunComfy image generation skill is a smart router across the RunComfy image-model catalog — FLUX 2 (Klein 9B/4B, Pro, D...

RunComfy CLI on RunComfy. The `runcomfy` CLI is one binary, one auth, hundreds of RunComfy model endpoints — image generation on RunComfy, image edit on RunC...

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 — p...

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice ve...

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...

Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenLabs Music turns a style description plus structu...

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, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-dr...

Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its o...