nomyo.ai:vision
nomyo.ai:vision is NOMYO AI’s multimodal model — it understands images and generates them. It analyzes visual content with precision, produces structured descriptions, and generates images on demand. Where other models work from text alone, vision works from the full picture.
Vision is available through the NOMYO AI platform and deployed within skandha wherever workflows involve visual data: product catalogues, document imaging, media production, visual QA and creative generation.
11B parameters · 16k context window
Has access to: Image Generation
What vision is good at
- Image analysis and structured description extraction
- Generating product descriptions from visual and metadata inputs
- Ad creative and visual content generation
- Document and diagram interpretation
- Supporting creative and media production workflows
Image generation formats
| Format | Resolution |
|---|---|
| Default | 1024×1024px |
| Square | 1440×1440px |
| Landscape | 1024×768px |
| Landscape large | 1440×1024px |
| Portrait | 768×1024px |
| Portrait large | 1024×1440px |
Generated images are automatically upscaled 2× with less than 1% quality loss. 4× upscaling is available on request.
Where it fits in platform deployments
In skandha vertical deployments, vision handles the visual layer of knowledge work — extracting structured data from images, generating visual assets from product data, supporting any workflow where the input or output is not purely text. Expert knowledge domains that work with products, documents or media are natural fits.
Subscription required
Access to nomyo.ai:vision requires a subscription. See pricing →
nomyo.ai:vision is accessible via the nomyo SDK (pip install nomyo) at api.nomyo.ai.