Gemini Omni 1.2 Flash Reference to Video
Generate video from references with Gemini Omni 1.2 Flash. Give it up to 6 images of a person, a product or a style (some providers accept 10), plus up to 3 short reference clips for motion, and describe how they come together. Google tuned 1.2 for stronger reference adherence, so identities and products stay consistent across the clip, with native audio.
57% less than the priciest provider (7 compared). Same model, same output.
As of , Gemini Omni 1.2 Flash Reference to Video costs from $0.02 per second on Scenetra, billed at provider cost with no markup. Each run is priced across 15 providers and runs on the cheapest one that supports your settings.
Up to 6 reference images (some providers accept 10) for characters, products, style or scene.
Up to 3 short reference clips, 3 seconds or less each (only 1 for videos over 10 seconds). Their audio is ignored.
Duration
Length of the video in seconds (3-15; up to 10 with a last frame). Billed per second.
Resolution
360p is a fast, cheap draft; 720p is native; 1080p and 4k upscale the render.
Aspect Ratio
16:9 landscape or 9:16 vertical.
57% less than the priciest provider (7 compared). Same model, same output.
Your result renders here.
Use Gemini Omni 1.2 Flash Reference to Video via the API
One REST call per generation, routed to the cheapest provider and billed in credits at provider cost. Endpoints, request fields, code examples and pricing are in the full API reference.
What makes Gemini Omni 1.2 Flash Reference to Video different
Sound is part of the prompt
Gemini Omni 1.2 Flash renders dialogue, music and sound effects in the same generation as the picture. Put spoken lines in quotes, name the music mood, call out the sound effects, and they happen in the clip. There's no separate audio pass and no lip-sync step afterwards.
Up to 15 seconds, any whole second
Pick any length from 3 to 15 seconds, 50% longer than the previous Omni. Every provider bills per second with no base fee, so a 10-second 720p clip is $0.45 and a 15-second one $0.68.
Draft at 360p, finish in 4K
360p drafts cost $0.20 for 10 seconds, so you can iterate on the idea cheaply, then render the keeper at native 720p or upscaled 1080p ($0.50) and 4K ($1.10). Landscape 16:9 and vertical 9:16 are both supported.
Five modes in one family
Generate from text, animate a first frame (optionally into a last frame), guide it with up to 6 reference images and short clips, edit an existing video with one sentence, or extend a clip by 3 to 10 seconds. Every run goes to the cheapest provider for your settings, billed at cost with 0% markup.
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Describe the scene, action, camera and style, and the audio: dialogue, music and sound effects are rendered natively and directed through the prompt. | — |
| Duration | select | Duration of the video in seconds (3-15).3 · 4 · 5 · 6 · 7 · 8 · 9 · 10 · 11 · 12 · 13 · 14 · 15 | 8 |
| Resolution | select | 360p is a fast, cheap draft; 720p is native; 1080p and 4k upscale the render.360p · 720p · 1080p · 4k | 720p |
| Aspect Ratio | select | 16:9 landscape or 9:16 vertical.16:9 · 9:16 | 16:9 |
Pricing
From $0.02 per second
Pay per generation — only pay for what you use.
360p
$0.02/s
per second
720p
$0.045/s
per second
1080p
$0.05/s
per second
4K
$0.11/s
per second
What a video costs
| Duration | 360p | 720p | 1080p | 4K |
|---|---|---|---|---|
| 5 seconds | $0.10 | $0.23 | $0.25 | $0.55 |
| 10 seconds | $0.20 | $0.45 | $0.50 | $1.10 |
| 15 seconds | $0.30 | $0.68 | $0.75 | $1.65 |
Use cases
Social & UGC
- Talking-head product reviews
- Vertical 9:16 hooks with dialogue
- Trend reactions with music
- Creator-style showcases
Marketing & ads
- Short spots with voiceover
- Product teasers with sound effects
- Cheap 360p concept rounds
- Finals upscaled to 4K
Film & previz
- Dialogue scene sketches
- Shot extensions past 15 seconds
- Text-directed reshoots via edit
- First-to-last-frame transitions
Education & explainers
- Narrated micro-lessons
- Concept visualizations with music
- Language practice clips
- Illustrated how-to beats
Frequently asked questions
How many references can I use?+
Up to 6 reference images on every provider (some accept 10) and up to 3 reference clips of 3 seconds or less each. For videos over 10 seconds only one clip is allowed.
Can I use it for virtual try-on?+
Yes. A photo of a model plus product shots of the outfits works well. Describe the sequence in the prompt, for example the model trying on each outfit in turn.
Related models
Gemini Omni Flash
Google's Gemini Omni Flash generates 3-10 second videos with native audio from a text prompt. Dialogue, music, and sound effects are rendered in the same pass as the picture and directed purely through your prompt. Output is native 720p with optional 1080p or 4K upscaling, in 16:9 or 9:16.
View model →Kling 4.0
Kuaishou's Kling 4.0 generates cinematic 3-30 second videos with native audio at 720p or 1080p, in 16:9, 9:16, 1:1 or 21:9 widescreen. Animate a first frame through up to 8 keyframes into a last frame, or keep characters and objects consistent from reference images and clips.
View model →Seedance 2.5
ByteDance's Seedance 2.5 generates cinematic videos up to 30 seconds from text prompts with synchronized audio — voice, sound effects, and background music — built in by default. The newest Seedance generation, with mp4 or high-fidelity mov output for multi-round editing pipelines.
View model →Wan 3.0
Alibaba's Wan 3.0 generates up to 30 seconds of video in a single take, with native synchronized audio — dialogue, sound effects, and music — produced in the same pass as the picture. Pick any duration from 2 to 30 seconds, output at 480p, 720p, or 1080p, and choose from five aspect ratios or let the model frame the shot automatically.
View model →Start creating with Gemini Omni 1.2 Flash Reference to Video
Use Gemini Omni 1.2 Flash Reference to Video alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started