v1.1.0 — gpt-image-2 support

Changes

• New default OpenAI model: gpt-image-2
• Added gpt-image-1-mini (lightweight OpenAI model)
• --resolution for gpt-image-2: accepts either WxH (e.g. 2048x1152) or an aspect ratio (e.g. 3:2, maps to a ~2K preset)
• Client-side validation of gpt-image-2 dimensions: multiples of 16, max edge 3840px, long:short ratio ≤ 3:1, total pixels between 655,360 and 8,294,400
• Older OpenAI models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini) continue to reject --resolution with a clear error

Install / update

dotnet tool update --global ImageGenCli