Foundry Agent Service tool, available out of the box, that lets an agent create pictures from text by pairing an orchestrator model with a gpt-image-1 deployment. It should not be confused with an input content type.
Also called image_generation.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Image generation tool in context, with comparison tables and the common traps.
Terms in this definition
- Foundry Agent Service
Fully managed Microsoft Foundry offering in which prompt, voice and hosted agents are created, deployed, run and scaled. Models, tools, guardrails, versioning, tracing and network isolation all come built in.
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).
- Agent
A specialised form of Microsoft Copilot set up for one particular job, pairing instructions with knowledge and skills. You can create one in Copilot Studio, SharePoint or Agent Builder, and administrators control them from the Microsoft 365 admin center.
- CRUD
Shorthand for create, read, update and delete, the four basic things you do with data. Data-plane roles in Azure Cosmos DB, for instance, authorise those operations on items.
- Pairing
Deployment pipelines link an item in one stage to its counterpart in the next. Deploying overwrites a linked item, but an unlinked item that just shares its name gets copied across as a duplicate.
- Orchestrator
Software, Kubernetes being an example, that looks after large numbers of containers throughout their life by scheduling, scaling, repairing and updating them.
- gpt-image-1
OpenAI's text-to-image model series, which took over from DALL-E in Azure. The first gpt-image-1 preview is retiring on 23 October 2026, so newer models such as gpt-image-2 or gpt-image-1-mini are used for new projects.
- Model deployment
Inside a resource, each deployment is a named copy of a Foundry model with its own TPM quota and deployment type. Requests identify the model by this deployment name.