ProductMicrosoftConfirmed
Story 8 of 16 in the Thursday 19 November editionMicrosoft previews Canvas workspace on MAI Image 2.7 Flash
Live in limited experimental preview on MAI Labs from 19 November 2026, generating images in 10 to 20 seconds with object-level selection and sketch edits.

Microsoft (Microsoft AI) launched Canvas on 19 November 2026 as a limited experimental preview on MAI Labs (labs.microsoft.ai/?model=canvas), introducing an interactive visual workspace powered by its new MAI Image 2.7 Flash model two days after Microsoft unveiled seven MAI models and Maia 300 at Ignite 2026. Users start from a text description in the side panel, an uploaded photograph, a rough sketch or starter presets including Leopards at dawn, Blossom to honey and Rainy reading nook, producing one image per run in about 10 to 20 seconds.
Direct object selection, sketch-to-diagram conversion and preview scope
Instead of regenerating an entire composition from scratch when refining details, Canvas lets users turn rough sketches into structured diagrams, click directly on an object inside the generated frame or swap a single word in the prompt panel to update just that element while keeping surrounding layout intact.
Microsoft notes that MAI Labs hosts experimental model previews where sessions are ephemeral and generated runs are not saved permanently to an account canvas. Microsoft has not announced standalone API access or token pricing for MAI Image 2.7 Flash.
Key details
- Underlying model and host
- MAI Image 2.7 Flash inside MAI Labs (labs.microsoft.ai/?model=canvas)
- Generation speed and output
- Roughly 10 to 20 seconds per run, producing one image per generation
- Supported editing inputs
- Text prompts, uploaded photos, sketches, word edits and direct object selection
Release details & context
Ephemeral MAI Labs sessions and experimental browser workflow
MAI Image 2.7 Flash runs inside Microsoft AI’s experimental MAI Labs sandbox alongside a dedicated model picker, operating separately from commercial cloud deployments so users can test interactive image-editing surfaces directly in the browser.
Because Canvas displays an explicit notice that outputs are not persisted to a saved canvas between visits, users testing diagram conversions or multi-step photo edits must download intermediate images locally before closing or reloading the tab.
Sources
- PrimaryMicrosoft AI MAI Labs: Canvaslabs.microsoft.ai
- On XMicrosoft AI (@MicrosoftAI) Canvas with MAI Image 2.7 Flash announcement on Xx.com
Microsoft release timeline (9 launches tracked)
- Microsoft launches MAI-Image-2.7 in preview and makes MAI-Image-2.6 generally available
Microsoft introduced MAI-Image-2.7 in preview and brought MAI-Image-2.6 and 2.6-Flash to general availability in Azure AI Foundry.
- Microsoft brings the multi-model Copilot harness to Microsoft Foundry
Microsoft exposes the Rust-based Copilot harness in Foundry as an SDK and managed service supporting 20+ models, MCP tools, and BYOK deployments.
- Microsoft AI introduces MAI Transcribe 2 speech model at $0.10 per audio hour
Microsoft AI launches MAI Transcribe 2 across 60 languages at $0.10 per batch hour, transcribing 1 hour in 10 seconds at a 5.2% FLEURS WER.
- Microsoft unveils seven MAI models, Maia 300, Microsoft IQ and Autopilot
Microsoft launches seven MAI models, Azure MAI Licensed Weights, Maia 300 silicon, Microsoft IQ with Retriever 1 and Copilot Autopilot at Ignite 2026.

