TextOpenAI
Prompt, chat, and multimodal text nodes
Models you dropon the canvas.
Text, image, video, audio, and utility nodes. Wire them into a workflow — then save, share, or publish as an API.
OpenAI
Google
Anthropic
Black Forest Labs
Kuaishou / Kling
Seedream
Omni Human
Wan
Seedance
HappyHorse
Realtime TTS
Video Combiner
Batch Generation
AI ArchitectEvery model on one grid.
Search text, image, video, audio, and publish triggers.
TextTextClaude
Long-context planning and rewrite passes
PrText
Prompt Input
Seed text that starts a media pipeline
ImageFlux Image
Stills from a prompt or reference
ImImage
Image Upscale
Sharpen frames before video or export
ReImage
Reference Image
Style lock from a still or board
VideoVeo Video
Clips from text or keyframes
VideoVideo Combiner
Stitch shots into one cut
LiVideo
Lip Sync
Match dialogue to generated faces
AudioSpeech
Voiceover from script or lyrics
MuAudio
Music Gen
Score beds that follow clip length
WeAPI
Webhooks
Start a pipeline when an event arrives
PuAPI
Published API
Trigger a saved workflow with an API key
UtilityAI Architect
Plain language in. Full pipeline out.
Get started
Drop a model on the canvas.
Wire image, video, and voice on a canvas. Batch-run the job, or let Architect build it from a brief.
