On June 30, Google began offering its image-generation model "Nano Banana 2 Lite" and its video generation and editing model "Gemini Omni Flash" to developers. Both models are available the same day through Google AI Studio and the Gemini API.
June 30 · Google
Google ships two new generative-media models for developers
Nano Banana 2 Lite — the fastest, cheapest Gemini image model — and Gemini Omni Flash, an "any-to-any" video generation and editing model, both arrive the same day via AI Studio and the Gemini API.
~4s
Text-to-image generation time (Nano Banana 2 Lite)
$0.034
Per 1,000 images generated
10s
Max 720p video, audio-synced (Omni Flash)
Nano Banana 2 Lite
Image generation / editing
Input
Text, image
Output
Image
Speed / price
~4s · $0.034 / 1,000 images
Gemini Omni Flash
Video generation / editing
Input
Text, image, video, audio
Output
Up to 10s, 720p video (audio synced)
Status
Public preview
An "any-to-any" multimodal pipeline
Omni Flash fuses Gemini's reasoning with generative media — accepting four input types and producing synchronized output.
Inputs
Text · Image
→
Reasoning
Physics & context
→
Output
10s 720p video
Praised by developers
High image quality at fast speed
Easy editing — compositing live-action with illustration styles
Character consistency & conversational video editing
Current limitations
Low fidelity to reference images; prompts sometimes ignored
Omni Flash can add elements absent from the source video
Safety-filter refusals; poor reproducibility in fine edits
Continue reading The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in ✓ Signed in — this article isn’t included in your current plan.Unlocking the full article…