Google: gemini-3.1-flash-image and gemini-3-pro-image reach GA — with video-to-image generation support
Google announced General Availability (GA) of two native visual models from the Gemini API on May 28, 2026: gemini-3.1-flash-image for efficient image generation and gemini-3-pro-image for high performance. A new feature is the video-to-image capability in the flash variant, which generates thumbnails, movie posters, and infographics from video files or YouTube URLs. Preview versions of both models are being deprecated on June 25, 2026.
This article was generated using artificial intelligence from primary sources.
Google announced the General Availability (GA) of two native visual models from the Gemini API ecosystem on May 28, 2026. The transition from preview to production status means teams can build commercial applications relying on API stability and contractual service levels.
What does GA status mean for gemini-3.1-flash-image and gemini-3-pro-image?
gemini-3.1-flash-image is designed as an efficient option for image generation — lower latency and lower computational cost make it suitable for applications requiring high-volume generation. gemini-3-pro-image targets high performance and output quality, aimed at creative industrial applications where quality takes precedence over speed.
Both models are available to development teams through the standard Gemini API, enabling integration into existing multi-modal pipelines that already use Gemini models for text or audio.
How does gemini-3.1-flash-image generate images from video content?
The most significant new capability of the flash variant is video-to-image generation. Developers can pass a video file as multimodal input — via direct upload or as a public YouTube URL — along with a text prompt, and the model generates visual derivatives from that content.
Applications Google mentions include: YouTube thumbnail generation, creation of cinematic movie posters from trailer material, and production of summary infographics from video presentations. This extends the Gemini API beyond the static text-to-image approach toward dynamic video content as a source of inspiration.
What happens to the preview versions?
gemini-3.1-flash-image-preview and gemini-3-pro-image-preview have been deprecated with a shutdown date of June 25, 2026. Developers using preview model IDs in production code must migrate to the GA versions — gemini-3.1-flash-image and gemini-3-pro-image — before that date to avoid service interruption.
GA versions provide stable API contracts and long-term support, unlike preview versions which were subject to change without prior notice.
Frequently Asked Questions
- What is gemini-3.1-flash-image and how does it differ from gemini-3-pro-image?
- gemini-3.1-flash-image is Google's native visual model optimized for efficiency and speed in image generation, while gemini-3-pro-image delivers higher performance and quality at a greater computational cost. Both reached General Availability (GA) on May 28, 2026.
- How does video-to-image generation work in the Gemini API?
- Users can pass a video file (via direct upload or as a public YouTube URL) as multimodal context along with a text prompt, and gemini-3.1-flash-image generates images such as thumbnails, movie posters, or summary infographics from the video content.
- When are the preview versions of the Gemini visual models being deprecated?
- The preview versions — gemini-3.1-flash-image-preview and gemini-3-pro-image-preview — are deprecated with a shutdown date of June 25, 2026. Developers must migrate to the GA versions by that date.
Sources
📬 AI news in your inbox
A daily digest built your way — pick topics, sources and cadence. One-click unsubscribe.