All models

GoogleVideo

Gemini Omni Flash

Fast video with synchronized audio from text, a still image, references, or a motion clip.

video/gemini-omni-flash
Try it in StudioUse with your agent or API

In the workshop from @Image2, the moss creature from @Image1 hops onto the workbench, finds the brass lantern from @Image3, lifts it with both twig hands and its face lights up in the warm glow. Locked-off medium shot. One continuous shot, no cuts. No readable text, no signs with letters, no screens showing people.

Price
from 10 credits / second
Typical time
about 46 s
Makes
Text to video, Image to video, Reference to video, Video to video
Clip length
4 to 10 s

Best for

Gemini Omni Flash is Google's fast multimodal video model. In Summer it covers four jobs from one model: text to video, image to video, video from up to ten subject and style references, and restyling a short motion clip. Version 1.1 ranks higher and suits scenes without realistic faces best.

  • Trailer and teaser shots while the game is still a prototype.
  • Animating key art or a character portrait into a short loop for a menu or store page.
  • Keeping one character consistent across several cutscene shots by feeding reference images.
  • Restyling a rough capture of your own gameplay into a different look for mood tests.

Put it together

Where Gemini Omni Flash fits in a game, with the models it works well with. Your agent runs every step.

Price

ModeModelPrice
Text to videoGemini Omni Flash 1.110 credits / second
Image to videoGemini Omni Flash 1.110 credits / second
Reference to videoGemini Omni Flash 1.1 References10 credits / second
Video to videoGemini Omni Flash 1.110 credits / second
Text to videoGemini Omni Flash~12.5 credits / second
Image to videoGemini Omni Flash~13 credits / second
Reference to videoGemini Omni Flash~13 credits / second
Video to videoGemini Omni Flash~13 credits / second

Paid from your Summer credits; ~ marks a typical estimate for token-priced output.

Use it from code or your agent

Sign in once with summer login. Your agent or your code then runs it with your paid credits.

npx -y summer-engine@latest login
npx -y summer-engine@latest api run video/gemini-omni-flash \
  --input '{"prompt":"a dragon circling a castle at dawn","duration":5}' \
  --download .

video/gemini-omni-flash: $0.125 per second of video. Paid from your Summer credits.

Inputs

What input takes for video/gemini-omni-flash. Send only what you need; Summer fills in tested defaults.

  • promptstringup to 4000 characters

    What happens in the clip. Needed without imageUrl.

  • imageUrlstringup to 2048 characters

    A public image URL to animate (image to video).

  • endImageUrlstringup to 2048 characters

    With imageUrl: the last frame. The same image as imageUrl makes a seamless loop. Models with an end frame: Seedance, Kling 3, Wan, Vidu, LTX 2.5, Luma, MiniMax.

  • referenceImageUrlsarray of string1 to 10 items

    Reference to video: public images of the characters, props or style to keep (with a reference model, e.g. kling-4-ref). Motion transfer: the character to move.

  • videoUrlstringup to 2048 characters

    An input clip (public URL, at most 20 s): restyle or reframe it, move a character with its motion, or add sound to it (e.g. kling-video-to-audio). Billed on the clip's length.

  • durationintegerDefault 5 · 1 to 20

    Seconds; the model renders its nearest supported length.

  • aspectRatioenumDefault 16:9
    • 16:9
    • 9:16
    • 1:1
    • 4:3
    • 3:4
    • 21:9
    • 3:2
    • 2:3
    • auto
  • negativePromptstringup to 1000 characters

    What the clip must not show.

  • resolutionenum

    Only a quality the model offers; leave out for its default.

    • 720p
    • 1080p
    • 4k
    • 480p
    • 768p
    • 2k
    • 768P
    • 1080P
    • 480P

Model docs · Summer API docs · Set up the Summer MCP server · Try it in the browser

Questions

What is Gemini Omni Flash good for in game development?
Gemini Omni Flash is Google's fast multimodal video model. In Summer it covers four jobs from one model: text to video, image to video, video from up to ten subject and style references, and restyling a short motion clip. Version 1.1 ranks higher and suits scenes without realistic faces best. Typical game uses: trailer and teaser shots while the game is still a prototype; animating key art or a character portrait into a short loop for a menu or store page; keeping one character consistent across several cutscene shots by feeding reference images; restyling a rough capture of your own gameplay into a different look for mood tests.
How much does Gemini Omni Flash cost in Summer?
In Summer Studio: Gemini Omni Flash 1.1 (text to video): 10 credits / second; Gemini Omni Flash 1.1 (image to video): 10 credits / second; Gemini Omni Flash 1.1 References (reference to video): 10 credits / second; Gemini Omni Flash 1.1 (video to video): 10 credits / second; Gemini Omni Flash (text to video): ~12.5 credits / second; Gemini Omni Flash (image to video): ~13 credits / second; Gemini Omni Flash (reference to video): ~13 credits / second; Gemini Omni Flash (video to video): ~13 credits / second. Prices marked ~ are typical estimates because the provider bills by tokens or output size. It is charged from your Summer credits.
What can Gemini Omni Flash generate, and how long are the clips?
In Summer, Gemini Omni Flash supports text to video, image to video, reference to video, and video to video. Generated clips run 4, 5, 6, 8, and 10 seconds, in 16:9 and 9:16 aspect ratios at 720p, 1080p, and 4K. Video-to-video and motion-transfer results follow the length of your source clip.
Can I use Gemini Omni Flash from Claude Code, Cursor or Codex?
Yes. Connect the Summer MCP server to Claude Code, Cursor, Codex or another MCP client, then ask your agent to generate with summer_generate_video with model: "gemini-omni-flash-1.1". Setup instructions are at summerengine.com/mcp.
Where do Gemini Omni Flash results go?
Every generation is saved to your Summer asset library. From there you can download it or bring it into a Summer Engine project.