agentspace-so
Official@agentspace-so
Provides specialized model routing and execution endpoints for high-fidelity generative image, video, and audio synthesis tasks.
Agent Skills by agentspace-so
Showing 29 vetted skills indexed across 1 GitHub repositories.
agentspace-soflux-2-klein
Generate images from text prompts using Flux 2 Klein on RunComfy.
agentspace-sovideo-extend
Extend existing video clips via Veo 3-1 extend-video endpoints.
agentspace-sohappyhorse-1-0
Translate user prompts into HappyHorse 1.0 text-to-video API payloads for RunComfy.
agentspace-soace-step
Generate, inpaint, and outpaint music tracks via RunComfy ACE Step endpoints.
agentspace-solipsync
Generate lip-synced videos from audio or scripts via RunComfy CLI.
agentspace-sogpt-image-edit
Edit images with GPT Image 2 while preserving identity and rewriting embedded text.
agentspace-sonano-banana-edit
Edit images via RunComfy CLI against the google/nano-banana-2/edit endpoint.
agentspace-socontrolnet-pose
Generate pose-conditioned images or videos using OpenPose, depth, or canny controls.
agentspace-soflux-kontext
Edit single images with Flux 1 Kontext Pro via RunComfy CLI.
agentspace-soimage-to-video
Route still images to RunComfy image-to-video models by intent.
agentspace-sowan-2-7
Generate lip-synced text-to-video clips via the RunComfy Model API.
agentspace-sonano-banana-2
Generate images from natural-language prompts via the RunComfy Model API.
agentspace-soelevenlabs-music-generation
Generate music tracks from style briefs and structured lyrics via ElevenLabs Music.
agentspace-soimage-outpainting
Extend images beyond their original canvas via RunComfy edit endpoints.
agentspace-sokling-3-0
Generate cinematic Kling 3.0 videos on RunComfy from text prompts or reference images.
agentspace-soai-image-generation
Route text-to-image and image-to-image requests to RunComfy model endpoints.
agentspace-soimage-inpainting
Perform mask-driven image inpainting to remove or replace image regions.
agentspace-soseedance-v2
Generate cinematic lip-synced videos from text and reference media via RunComfy.
agentspace-soai-avatar-video
Create avatar videos from audio or scripts via RunComfy model routing.
agentspace-soai-music
Route natural-language music requests to RunComfy text-to-audio or ACE Step endpoints.
agentspace-sovideo-outpainting
Extend video spatial canvas for aspect-ratio changes via RunComfy CLI.
agentspace-sovideo-inpainting
Remove unwanted objects across video frames via RunComfy prompt-driven region edits.
agentspace-sovideo-edit
Route video editing intents to RunComfy models and execute endpoints.
agentspace-soai-video-generation
Generate AI video clips from text, images, or Veo extensions via RunComfy CLI.
Frequently Asked Questions About agentspace-so
FAQPage SchemaWhat specific creative tasks are enabled by these endpoints?▼
These endpoints enable text-to-video generation, image outpainting, video frame inpainting, lip-syncing from audio, and music track synthesis. Users can perform complex edits like relighting, pose-conditioning, and spatial canvas extension for both static imagery and motion media.
Which personas benefit from these model routing capabilities?▼
Creative technologists, digital artists, and media engineers benefit from these capabilities. The registry provides a unified interface for routing requests to specialized generative models, allowing professionals to integrate high-fidelity visual synthesis into their production pipelines without managing individual model weights.
What are the prerequisites for executing these model requests?▼
Execution requires a valid RunComfy environment and access to the specific model endpoints. Users must provide structured prompts, reference media, or mask files depending on the task, and handle job polling and asset retrieval through the provided interface.