Image Generation
Generate images from text prompts across 8 built-in providers with a single API.
Image Editing (Img2Img, Inpainting, Upscaling)
Edit, upscale, and create variations of existing images across providers with one API.
Character Consistency
Generate images that maintain a consistent character identity across multiple outputs using reference images and face embeddings.
Style Transfer
transferStyle() restyles a source image after a style reference. It sends the provider both images: Replicate and Fal on FLUX.2, Stability on its style-transfer endpoint, OpenAI on two-image edits.
Vision Pipeline (OCR & Image Understanding)
VisionPipeline runs an image through up to five tiers: OCR (PaddleOCR or Tesseract.js), handwriting recognition (TrOCR), document layout (Florence-2), a cloud vision model called through generateText(), and an image embedding (CLIP). createVisionPipeline() builds a pipeline from the packages installed and the API keys in the environment.
Image Segmentation and Background Removal
Turn an image plus a prompt (text, point, box, or "segment everything") into
Audio Generation
AgentOS provides provider-agnostic APIs for generating music and sound effects from text prompts. Two high-level functions cover the full audio generation pipeline:
Provider Preferences
The ProviderPreferences helpers let a caller choose which media providers a call may use and in what order. generateImage(), generateVideo(), generateMusic() and generateSFX() take one MediaProviderPreference per call as providerPreferences.
Video Pipeline
AgentOS has three video functions, all exported from @framers/agentos: