@agentspace-so

runcomfy-cli wraps hundreds of ai model endpoints (image generation, video, editing, face-swap, upscaling) behind a single command-line interface with pluggable auth, multiple polling modes, and json output for scripting.

agentspace enables agents to share local folders and files via ephemeral or permanent urls, with browser-based viewing, commenting, and editing. works via single cli command, no account required.

image-inpainting enables mask-driven region edits (object removal, background replacement, retouching) via runcomfy cli, routing to z-image turbo when masks are provided and falling back to description-based models otherwise.

ai-avatar-video routes audio and images across five runcomfy models (omnihuman, wan, happyhorse, seedance) to generate talking-head and avatar videos, selecting the appropriate model based on user intent like dubbing, ugc ads, or character animation.

video-outpainting extends spatial canvas and aspect ratio through runcomfy cli, routing simple cases via wan 2-7 and delegating premium work to dedicated comfyui workflows for motion-aware fill.

intent-based router that maps image editing requests to one of four RunComfy models (Nano Banana, GPT Image 2, Flux Kontext, Z-Image Turbo), each optimized for different use cases like batch processing, multilingual text, precision edits, or inpainting.

video-inpainting performs region edits across frames via runcomfy cli, routing between three models for watermark removal, object deletion, and motion-continuous replacement using natural language prompts.

ai-image-generation routes text-to-image and image-to-image requests across 11+ models (FLUX 2, GPT Image 2, Nano Banana, Seedream, others) via runcomfy CLI, auto-selecting models by intent. covers installation and auth but lacks complete procedural detail.

lipsync routes audio-driven face animation across four endpoints (OmniHuman, Sync Labs, Kling, Creatify), selecting models by input type and quality tier. handles video dubbing, avatar generation, and in-pass speech synthesis via runcomfy CLI.

happyhorse-1-0 generates text-to-video clips with synchronized audio on runcomfy, supporting up to 1080p and multi-shot character consistency across six languages.

ai-music routes vocal and instrumental generation requests across elevenLabs and ACE Step models via runcomfy CLI, with audio editing via inpainting and outpainting. model selection is intent-aware but execution steps remain incomplete.

controlnet-pose routes pose-conditioned image and video generation across kling motion control, wan animate, and z-image controlnet lora. accepts openpose, dwpose, canny, or depth control inputs via runcomfy cli.

ace-step wraps stepfun-ai's open-weights music model for text-to-audio, inpainting, and outpainting via runcomfy cli. tag-driven composition supports 50+ languages and costs roughly 27x less than elevenlabs music.

gpt-image-2 wraps chatgpt's image generation (text-to-image, editing, style transfer) through a local codex cli, requiring an active chatgpt plus/pro subscription and no separate api keys.

video-edit routes edit requests to appropriate runcomfy models based on user intent, supporting restyle, motion transfer, and identity-stable swaps without model lock-in.

elevenlabs-music-generation wraps text-to-music synthesis via runcomfy cli, supporting 5-second to 5-minute generation with section control, but lacks actionable procedural detail.

flux-2-klein wraps black forest labs' distilled flux 2 model via runcomfy api, optimized for low-latency image generation without key management. intended for rapid iterative creative work rather than maximum quality output.

seedance-v2 is a bytedance multimodal video generator for short-form cinematic content with lip-sync, but the skill definition lacks procedural substance and is essentially marketing copy.

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 own…

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…

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's…

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…

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 —…

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 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),…

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

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…

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 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 with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so…

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

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the…

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…