scenario-gemini-omni

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Scenario Gemini Omni Video

Overview

概述

Gemini Omni, Google's video family on Scenario, splits its modes across catalog members instead of folding them into one model: a text and first-frame generator (ranked first for text-to-video in public arena voting at authoring time), a reference-to-video member for subject consistency, an edit member that restyles existing footage, and on the newer 1.1 Flash line an extend member that appends footage to a clip. Every member generates audio in the same pass. Pick the line and the member by mode with

search

, reading ids and descriptions rather than rank (the newer 1.1 members ranked below the original line at authoring time), then treat

model_schema_get

as the contract. Gemini image models are the

scenario-gemini-image

skill's domain; Gemini TTS belongs to audio.

Connection and the core loop: see the

scenario

skill; model-agnostic video work: the

scenario-video

skill. If a sibling skill named here is missing from your available skills, ask the user to install it (

npx skills add scenario-labs/skills --skill <name>

); unattended, proceed from tool schemas and flag the gap.

Gemini Omni是Google在Scenario上的视频模型系列，其不同功能模式分散在不同的目录成员中，而非整合到单个模型里：包括文本与首帧生成器（撰写本文时在公开投票中文生视频排名第一）、用于保证主体一致性的Reference-to-Video成员、可对现有素材重设风格的Edit成员，以及在较新的1.1 Flash系列中用于为片段追加素材的Extend成员。所有成员都可在同一次生成中产出音频。你可以通过

search

按模式选择系列和成员，优先查看ID和描述而非排名（撰写本文时较新的1.1成员排名低于原系列），之后以

model_schema_get

的结果为准。Gemini图像模型属于

scenario-gemini-image

技能的范畴；Gemini TTS则归属于音频类。

连接方式与核心循环：参见

scenario

技能；与模型无关的视频处理工作：参见

scenario-video

技能。如果你的可用技能中缺少这里提到的同类技能，请让用户安装（命令：

npx skills add scenario-labs/skills --skill <name>

）；若处于无人值守模式，则从工具schema继续执行并标记缺失项。

Quick reference

快速参考

Two lines at authoring time, Flash and 1.1 Flash, one member per mode (names from the live schemas):

Member	Mode	Inputs
Gemini Omni	text or first frame	`prompt` and/or `image` , plus optional `referenceImages` (up to 7); on 1.1 an optional `lastFrameImage` beside `image`
Reference-to-Video	consistent subjects	`referenceImages` required (1 to 7), `prompt` optional; on 1.1 a `referenceVideo` of 3 s or less can replace the images or join up to 5 of them
Edit	restyle a clip	`video` and a change `prompt` , both required; optional `referenceImages` (1 to 5)
Extend (1.1 only)	continue a clip	`video` required, `prompt` optional

At authoring time both generators took

duration

3 to 10 seconds (default 8) and

aspectRatio

16:9

9:16

. Edit exposes neither knob: length and shape follow the source clip. Extend inherits the shape too (no

aspectRatio

) but takes

duration

3 to 10 (default 6) as footage appended after the source, so an 8 s clip plus 6 returns about 14 s. The original Flash members render 720p only; the 1.1 Flash line adds

resolution

on every member:

360p

a faster draft tier,

720p

the default,

1080p

and

4k

upscaled. The tier does not move price (at authoring time a generation quoted the same at 360p and 1080p, and so did Extend), so a cheap draft is a shorter

duration

, not a lower tier. Seed and negative prompt exist nowhere in the family. Cost moves with

duration

, a first-frame

image

, Reference-to-Video's references, and Edit's and Extend's source clips; Edit spanned the family's widest cost range at authoring time and its jobs ran about twice as long, so

dry_run

before editing anything long.

撰写本文时有两个系列：Flash和1.1 Flash，每种模式对应一个成员（名称来自实时schema）：

成员名称	模式	输入项
Gemini Omni	文本或首帧	`prompt` 和/或 `image` ，以及可选的 `referenceImages` （最多7张）；1.1版本中可在 `image` 之外额外提供可选的 `lastFrameImage`
Reference-to-Video	主体一致性	`referenceImages` 为必填项（1-7张）， `prompt` 为选填；1.1版本中可使用时长不超过3秒的 `referenceVideo` 替代图片，或与最多5张图片搭配使用
Edit	片段重设风格	`video` 和变更 `prompt` 均为必填项；可选填 `referenceImages` （1-5张）
Extend（仅1.1系列支持）	片段续拍	`video` 为必填项， `prompt` 为选填

撰写本文时，两个生成器都支持3-10秒的

duration

（默认8秒），以及

16:9

或

9:16

的

aspectRatio

。Edit不提供这两个参数：时长和比例完全跟随源片段。Extend同样继承源片段的比例（无

aspectRatio

参数），但支持3-10秒的

duration

（默认6秒）作为追加在源片段后的素材时长，因此一段8秒的片段加上6秒追加内容后总时长约为14秒。原Flash系列成员仅支持720p渲染；1.1 Flash系列的所有成员都新增了

resolution

参数：

360p

为更快的草稿档位，

720p

为默认档位，

1080p

和

4k

为升档画质。档位不影响价格（撰写本文时，360p和1080p的生成报价相同，Extend也是如此），因此要生成低成本草稿应该缩短

duration

，而非降低分辨率档位。整个系列都不支持seed和negative prompt。成本随

duration

、首帧

image

、Reference-to-Video的参考素材、以及Edit和Extend的源片段变化；撰写本文时，Edit的成本范围是全系列最宽的，且任务运行时长约为其他模式的两倍，因此编辑长片段前请先执行

dry_run

。

Sound is prompted, not switched

音效由prompt控制，无单独开关

No member has an audio parameter: every clip arrives with generated dialogue, ambience, and effects, and the prompt is the only lever. On the generators, end the prompt with an explicit audio line naming what should be heard ("crackling campfire, distant owls") and put spoken words in quotes; leave it out and the model chooses for you. On Edit, never prompt audio: it regenerates to match the new look on its own.

所有成员都没有单独的音频参数：每段视频都会自动生成对话、环境音和音效，且prompt是唯一的控制手段。对于生成类模型，在prompt末尾明确添加一行音频描述，说明需要听到的声音（比如“噼啪作响的篝火、远处的猫头鹰叫声”），并将台词放在引号中；如果不添加音频描述，模型会自行决定。对于Edit模式，永远不要在prompt中提音频要求：它会自动重新生成与新视觉风格匹配的音频。

Identity from images, change from words

身份一致性来自图片，变化来自文字

Reference-to-Video takes the subject's look from

referenceImages

, and re-describing it in the prompt fights the images. Call the subject "the character" or "the product" and spend the words on action, setting, camera, and sound; several angles of one subject tighten the hold, distinct subjects share one scene, and with no prompt at all the subjects still appear. There is no first-frame anchor here: when the clip must open on an exact composition, pass that still as

image

on the base member, which also accepts references alongside it and, on 1.1, a

lastFrameImage

to interpolate towards (it needs the first frame).

Edit is the inverse: motion, camera path, and timing are locked from the source

video

, only the look moves. Lead the prompt with the change ("make it winter", "swap the red car for a vintage blue Beetle"), name the target concretely, and never ask for new choreography, cuts, or camera moves: those instructions will not take.

Reference-to-Video从

referenceImages

中获取主体的外观，在prompt中重新描述主体外观会与图片产生冲突。你可以将主体称为“the character”（角色）或“the product”（产品），把prompt的内容重点放在动作、场景、镜头和音效上；同一主体的多个角度可以增强一致性，不同主体可以共享同一场景，即使完全没有prompt，主体也会出现在视频中。该模式没有首帧锚定：如果视频必须以某个精确的构图开头，请将该静态图片作为

image

传入基础成员（基础成员也支持同时传入参考素材，且在1.1系列中还支持传入

lastFrameImage

用于向其插值过渡——前提是需要首帧）。

Edit模式则正好相反：动作、镜头路径和时序都由源

video

锁定，只有视觉风格可以改变。在prompt开头说明要做的变更（例如"make it winter"、"swap the red car for a vintage blue Beetle"），明确指出变更目标，永远不要要求新的动作编排、剪辑或镜头移动：这些指令不会生效。

Worked example: a mascot short with a consistent character

实操示例：制作角色一致的吉祥物短片

```
search
```
with
```
target="models"
```
,
```
query="gemini omni"
```
,
```
public=true
```
. Pick the member by mode, here
```
model_google-omni-flash-r2v
```
(a live hit at authoring time: re-discover each session).
```
model_schema_get
```
with that id: required fields, caps, and defaults before anything else.
```
upload_asset
```
two or three angles of the mascot (see the
```
scenario
```
skill) to get asset ids.

model_run

with that

model_id

dry_run=true

, and

parameters={"prompt": "The character skips across a rain-slick plaza, catches a falling leaf, and holds it up in triumph. Overcast soft light, low tracking shot. Audio: light rain, footsteps on wet stone, one bright chirp.", "referenceImages": ["asset_a", "asset_b"], "duration": 8, "aspectRatio": "16:9"}

; references and duration move the cost, so re-estimate after changing either.

Repeat
```
model_run
```
with
```
wait=false
```
, then
```
jobs_wait
```
with the returned job id, re-called with
```
pending_job_ids
```
on timeout, never a second
```
model_run
```
.
```
asset_display
```
the output and review it with sound: the audio is part of the deliverable.

使用
```
search
```
，设置
```
target="models"
```
、
```
query="gemini omni"
```
、
```
public=true
```
。按模式选择成员，本例中为
```
model_google-omni-flash-r2v
```
（撰写本文时的有效ID：每次会话都需要重新查找）。
使用该ID调用
```
model_schema_get
```
：首先确认必填字段、上限和默认值。
调用
```
upload_asset
```
上传2-3张不同角度的吉祥物图片（参见
```
scenario
```
技能），获取素材ID。

调用

model_run

，传入

model_id

、

dry_run=true

，以及

parameters={"prompt": "The character skips across a rain-slick plaza, catches a falling leaf, and holds it up in triumph. Overcast soft light, low tracking shot. Audio: light rain, footsteps on wet stone, one bright chirp.", "referenceImages": ["asset_a", "asset_b"], "duration": 8, "aspectRatio": "16:9"}

；参考素材和

duration

会影响成本，因此修改任意一项后都需要重新估算。

再次调用
```
model_run
```
，设置
```
wait=false
```
，然后使用返回的任务ID调用
```
jobs_wait
```
，如果超时则使用
```
pending_job_ids
```
重新调用，绝对不要重复发起
```
model_run
```
。
使用
```
asset_display
```
展示输出结果，并带音效审核：音频是交付物的一部分。

Common mistakes

常见错误

Describing the reference subject's appearance in the prompt: identity comes from the images; write action and setting around "the character".
Asking Edit for new motion, cuts, or re-timing: they are locked to the source; prompt only the look change.
Passing
```
duration
```
or
```
aspectRatio
```
to Edit, or
```
aspectRatio
```
to Extend: not in their schemas; the output follows the source clip.
Hunting for an audio toggle: none exists; steer sound in the prompt or accept the model's choice.
Restating a first-frame
```
image
```
as a static scene: describe the motion continuing from it.
Packing a multi-scene story into one run: 3 to 10 seconds holds one continuous beat; carry a beat past 10 seconds with Extend, or sequence shots with the
```
scenario-video-assembly
```
skill.

在prompt中描述参考主体的外观：身份一致性来自图片；请围绕“the character”撰写动作和场景相关内容。
要求Edit模式生成新动作、剪辑或重新调整时序：这些都与源素材绑定；仅可通过prompt要求视觉风格变更。
向Edit传入
```
duration
```
或
```
aspectRatio
```
，或向Extend传入
```
aspectRatio
```
：这些参数不在其schema中；输出会跟随源片段的属性。
寻找音频开关：不存在该功能；请通过prompt控制音效，或接受模型的自动选择。
将首帧
```
image
```
当作静态场景重复描述：请描述从该帧延续的动态内容。
将多场景故事塞进一次生成任务中：3-10秒只能承载一个连续镜头片段；如果需要超过10秒的片段，可以使用Extend续拍，或使用
```
scenario-video-assembly
```
技能拼接镜头。