infinite-talk/fast/multi
Transform speech into lifelike video avatars with expressive, synced motion.
This model takes one picture and a written direction, then animates the image into a short cinematic clip with sound baked in. It sits inside Google's Gemini Omni Flash family, which also spans text-to-video, video editing, and reference-to-video; this RunComfy page runs the image-to-video task.
Because the model reasons about how the physical world behaves, movement stays coherent from the first frame onward instead of drifting or warping as the shot plays out.
Inputs match the RunComfy OpenAPI Input schema for the image-to-video task.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | descriptive text | Describes how the input image should move or change |
| image_url* | Yes (*) | string (image URI) | — | jpg, jpeg, png, webp | The still image to animate |
| aspect_ratio | No | string | 16:9 | 16:9, 9:16 | Aspect ratio of the generated video |
| duration | No | integer | 8 | 3-10 (seconds) | Length of the generated video in whole seconds |
Billing is based on the length of the generated clip:
Transform speech into lifelike video avatars with expressive, synced motion.
Cinematic 4K image-to-video at $0.42 per second of output.
Generate lifelike motion visuals fast with Dreamina 3.0 for designers.
Film-quality Seedance 2.0 grade video generation with stunning visual fidelity and cinematic motion
Create realistic motion visuals with Veo 3.1's sleek AI video conversion.
Animate stills into native 4K cinematic clips with start-end frame guidance and synchronized sound.
Gemini Omni Flash Image to Video takes a single still image and a text prompt, then animates the picture into a short clip with synchronized audio. It infers natural motion for the subject and scene, so you can turn one frame into a moving, sound-backed shot without a separate animation or audio step.
It works well for turning still photos into short social clips, testing camera moves and pacing from a reference image, and prototyping audio-visual concepts quickly. Creators, marketers, and film or game teams often use Gemini Omni Flash Image to Video to explore motion and atmosphere before committing to a full production pass.
The model generates sound in step with the animated picture, including speech, ambient effects, and music where appropriate. You can steer this in the prompt with Gemini Omni Flash Image to Video by naming the dialogue tone or background sound you want, or asking for no dialogue when you need a quiet clip.
Starting from an uploaded image gives you tighter control over the opening composition and subject identity than a text-only prompt. With Gemini Omni Flash Image to Video, the still anchors the look while the prompt directs how the scene moves, which is useful when you already have a specific frame in mind.
Gemini Omni Flash Image to Video supports 16:9 landscape and 9:16 portrait framing, with clip lengths from 3 to 10 whole seconds. Check the current RunComfy parameter panel for the exact options, since available settings can change over time.
You provide one input image plus a text prompt describing the motion; supported image formats include jpg, jpeg, png, and webp. For any limits not listed in the panel, review the RunComfy parameter fields, since some constraints may vary by provider settings.
Yes. You can prototype Gemini Omni Flash Image to Video in the RunComfy AI model UI, then call the same model via the RunComfy HTTP API with identical parameters for automation and production. This lets you move from testing to integration without hosting or scaling the model yourself.
Generations with Gemini Omni Flash Image to Video are billed by clip length at $0.14 per second of generated video, and consume usd or credits on your RunComfy account. New users typically receive a free trial amount, and you can review current rates in the Generation section of this page.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
