Images

​

Understand Images

Vision is Notis’s image understanding capability that enables our AI to “see” and analyze the content of images you share. When you upload an image, the Vision tool processes it and can describe, analyze, or extract information from the visual content.

​

Features

• Understand image content (people, objects, scenes, text, charts, screenshots)
• Extract structured information (business cards, receipts, product labels, handwritten notes)
• Analyze visual elements (data visualizations, design elements, concepts)

​

Examples

“Extract information from this restaurant receipt, including the restaurant name, date, time, items purchased, and payment details.” “Digitize this business card information including name, title, company, contact details, and website.” “Analyze this quarterly sales chart and provide a detailed breakdown of the numbers along with growth percentages between quarters.” “What is this plant and how much should it be watered every week?”

​

Generate & Edit Images

Notis can create new images from your description and edit images you’ve already shared. Tell Notis what you want to make, share any reference images, and describe what should change or stay the same.

​

Choose the right image model

ChatGPT Image — Flare is the default for everyday image creation and editing. Use it for social posts, quick concepts, illustrations, and routine changes to an existing image. ChatGPT Image — Sunburst takes longer and gives you more precision for detailed creative work. Ask Notis to use Sunburst when keeping a face, logo, product, or layout consistent matters more than speed. You can also ask for it when refining a finished campaign image across several edits. Nano Banana Pro is available for Google’s image controls and optional Google Search grounding. Ask for it when you want those features.

​

Shared features

• Generate images from voice or text instructions.
• Edit images you sent, that Notis created previously, or that live in your Notion databases.
• Save the result directly into a Notion media property in the same turn.

​

Nano Banana Pro capabilities

• Aspect ratios — 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
• Resolution tiers — 1K, 2K, or 4K for poster- and print-quality output.
• Multiple reference images — combine several inputs in a single edit (e.g., place a product on a new background, mix two style references, blend characters).
• Google Search grounding — optional real-world grounding so the model can render up-to-date facts (logos, charts, places, current events) instead of hallucinating them.
• High-fidelity text — reliably renders readable text and labels inside the image, ideal for infographics, slides, and UI mockups.

​

ChatGPT Image capabilities

• Flexible sizes — ask for a square, portrait, landscape, or a custom size such as 1536 × 864. Notis checks the dimensions before generating. Very large images above 2560 × 1440 are experimental.
• Quality choices — low for quick drafts, then medium, high, xhigh, or max for more detail. Leave it on auto when you want the model to choose. Higher quality can take longer and use more of your budget.
• Transparent backgrounds — create transparent PNGs for logos, stickers, and assets you want to place on another background.
• Multiple outputs — ask for up to four variations at once.
• Reference images and follow-up edits — share your source images and say what to preserve. For another edit, refer to the latest version and describe the next change. Results can still need checking, especially for exact text and brand details.

Flare and Sunburst have the same per-token rates, but the total cost can differ with the model, quality, dimensions, and reference images. Image creation uses your Notis usage budget even when another agent helps prepare the prompt.

​

Examples

Generate new images: “Generate an image of a cat riding a bicycle in a cartoon style.” “Create a 16:9 4K infographic of this quarter’s sales numbers and save it in the media property.” “Make a transparent PNG of a blue rocket I can drop into a slide.” “Generate 3 variations of a minimalist logo for a coffee shop.” “Create a poster of the current weather in Tokyo.” (uses Google Search grounding for real-world data) Edit existing images: “Edit this image to add a rainbow in the background.” “Combine these two product photos onto the same beach background.” “Remove the text from this image and replace it with our company logo, keeping the logo crisp.” “Change the background color to blue while keeping the subject’s face exactly as it is.” “Use Sunburst to replace the headline in this campaign image, preserving the logo, product, and layout.”