moda-video-clip

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

moda-video-clip

PREREQUISITE — load
moda-core
once per session (step-0, write contract, free/metered map). Already loaded? Skip ahead. If you cannot load it, the non-negotiables: run

moda doctor --json

before anything;

moda brand list

before creating; every write carries the latest revision — on

stale_revision

, re-read and retry once (it heals); send the canvas link the moment it exists; stuck or failed?

moda ask "<question>"

— free and fast, never guess.

前置要求 — 每个会话仅需加载一次
moda-core
（步骤0，签署协议，免费/按使用量计费对照表）。已加载？直接跳过。若无法加载，必须执行以下操作：先运行

moda doctor --json

；创建前运行

moda brand list

；每次写入操作需携带最新版本号——遇到

stale_revision

错误时，重新读取并重试一次即可解决；画布链接一经生成立即发送；遇到卡顿或失败？使用

moda ask "<question>"

——免费且响应迅速，切勿自行猜测。

Cards before knobs

先查能力卡片，再调参数旋钮

--model

is REQUIRED on every call and there is no "auto". Read the capability cards FIRST and copy values verbatim — guessing a duration, ratio, resolution or

--model-params

value is how a call 422s.

```
moda media models
```
— one card per model: modes (prompt→video, image→video, reference→video, extend), duration and resolution envelopes, aspect ratios, audio behaviour, billing basis.
Pin the knobs on EVERY call: explicit
```
--duration
```
(omitting it reserves the model's LONGEST clip) and the resolution the pass needs. Knobs snap server-side — read
```
applied
```
and
```
adjustments
```
on the result, never assume.
Nothing is charged until a finished render is collected, so
```
--no-wait
```
+
```
moda task status [TASK_REF] --wait
```
is how several drafts run at once. A re-run of the same call replays the existing render instead of paying twice; a deliberate retake needs a changed knob (
```
--seed
```
, or a new prompt).

每次调用必须指定

--model

，无“自动”选项。请先仔细阅读能力卡片，并严格复制参数值——若随意猜测时长、比例、分辨率或

--model-params

参数值，会导致调用返回422错误。

```
moda media models
```
— 每个模型对应一张卡片：包含生成模式（文本转视频、图片转视频、参考视频生成、视频扩展）、时长与分辨率范围、宽高比、音频行为、计费规则。
每次调用都要明确设置参数：指定
```
--duration
```
（若省略，将占用模型支持的最长片段时长）以及当前步骤所需的分辨率。参数会在服务器端自动适配——请查看返回结果中的
```
applied
```
和
```
adjustments
```
字段，切勿自行假设。
仅在收集到完成的渲染结果时才会扣费，因此使用
```
--no-wait
```
+
```
moda task status [TASK_REF] --wait
```
可同时运行多个草稿。重复调用相同指令会复用已有渲染结果，无需重复付费；若需重新生成，需修改参数（如
```
--seed
```
或新的提示词）。

Sizes and defaults

尺寸与默认设置

Pass	Duration	Resolution	Audio
Draft	shortest legal (≈4 s)	720p	silent where silence is a price axis
Hero	what the deliverable needs	what it will be seen at	per the card
Upscale	—	one tier up, on the winner only	unchanged

Hard edges, facts not preferences: video models mangle text, prices and logos — real type and brand marks go on the canvas, never in a prompt (that is moda-video-motion's job). There is no free-form video-to-video edit: a source clip is a generation reference, an

--extend-video

base, or the subject of

upscale-video

reframe-video

阶段	时长	分辨率	音频
草稿	最短合法时长（约4秒）	720p	若静音可降低成本则设为静音
最终版本	交付需求时长	适配观看场景的分辨率	遵循模型卡片说明
超分辨率提升	—	仅对选中的优质版本提升一个分辨率层级	保持不变

明确规则，而非主观偏好：视频模型会扭曲文字、价格和logo——真实文字和品牌标识需添加到画布中，切勿写入提示词（这是moda-video-motion的功能范围）。不支持自由形式的视频转视频编辑：源视频只能作为生成参考、

--extend-video

的基础，或用于

upscale-video

reframe-video

操作。

Recipe — the draft ladder (the DEFAULT for anything a user will see)

操作流程——草稿迭代法（面向用户内容的默认流程）

Start assets, if any:

moda brand show [BRAND_REF] --json

for durable logo refs (LOOK at them first); a canvas frame via

moda export [CANVAS_REF] --format png --page [N] --pixel-ratio 2 -o frame.png

; user footage via

moda file upload [clip.mp4]

Draft.

moda media generate-video --prompt "[one complete instruction: subject, motion, camera, style, mood]" --model veo-3.1-lite --duration 4 --resolution 720p --no-generate-audio -o draft.mp4

— it comes back while you can still change your mind.

Look at it.
```
moda media video-frames draft.mp4 --count 4 -o frames/
```
— FREE, and the only way to SEE a render. Judge the frames against the brief; never present a clip you have not looked at.
Fix, don't escalate. A draft that missed is nearly always a PROMPT problem: change the prompt, re-draft on the fast lane. Stepping up a tier buys a sharper version of the wrong clip.
Commit. Only the surviving direction, at the length and resolution the deliverable needs, on the model the ask deserves:
```
moda media generate-video --prompt "[revised]" --model [HERO_MODEL] --duration [N] --resolution [TIER] -o hero.mp4
```
.

Frame-check the hero the same way, then enhance the WINNER only:

moda media upscale-video hero.mp4 --resolution 1080p -o final.mp4

, or

moda media reframe-video hero.mp4 --aspect-ratio 9:16 -o vertical.mp4

Deliver: the result is a durable
```
file_…
```
. Fetch it with
```
moda file download [FILE_REF] -o [name].mp4
```
, hand over the path plus the usage receipt. Going on a canvas instead (type, a price, a logo, a cut)? Hand off to moda-video-motion —
```
<video>
```
markup is the only way clips land on a canvas.

准备初始素材（如有）：运行
```
moda brand show [BRAND_REF] --json
```
获取持久化logo引用（请先查看引用内容）；通过
```
moda export [CANVAS_REF] --format png --page [N] --pixel-ratio 2 -o frame.png
```
导出画布帧；通过
```
moda file upload [clip.mp4]
```
上传用户素材。

生成草稿。运行

moda media generate-video --prompt "[完整指令：主体、动态效果、镜头、风格、氛围]" --model veo-3.1-lite --duration 4 --resolution 720p --no-generate-audio -o draft.mp4

——快速返回结果，便于及时调整思路。

查看草稿。运行
```
moda media video-frames draft.mp4 --count 4 -o frames/
```
——免费操作，这是查看渲染结果的唯一方式。对照需求判断帧效果；切勿展示未查看过的片段。
修正问题，而非升级模型。草稿不符合需求几乎都是提示词问题：修改提示词，重新生成草稿。升级模型只会得到更清晰的错误片段，无法解决核心问题。
确认生成最终版本。仅为筛选后的方向生成最终版本，根据交付需求设置时长、分辨率，选择匹配需求的模型：
```
moda media generate-video --prompt "[修正后的提示词]" --model [最终版本模型] --duration [N] --resolution [分辨率层级] -o hero.mp4
```
。

用同样方式检查最终版本的帧，仅对优质版本进行增强：

moda media upscale-video hero.mp4 --resolution 1080p -o final.mp4

，或

moda media reframe-video hero.mp4 --aspect-ratio 9:16 -o vertical.mp4

。

交付：结果为持久化的
```
file_…
```
文件。通过
```
moda file download [FILE_REF] -o [name].mp4
```
获取文件，提供文件路径及使用凭证。若需添加到画布（文字、价格、logo、剪辑）？移交至moda-video-motion——
```
<video>
```
标记是视频片段添加到画布的唯一方式。

Examples

示例

"a 10-second product video" → ladder: draft, frames, hero render.
"animate our logo into a stinger" → image-to-video with the logo as
```
--image
```
.
"make this 6s clip longer" →
```
--extend-video
```
on a model whose card shows it.
"make the 16:9 into a story cut" →
```
reframe-video --aspect-ratio 9:16
```
.
"animate this quote / this headline" → not this lane: moda-video-motion sets real type on a canvas; a model would mangle it.

"10秒产品视频" → 流程：生成草稿、查看帧、渲染最终版本。
"将我们的logo动画化为收尾镜头" → 使用图片转视频模式，将logo作为
```
--image
```
参数。
"将这段6秒视频延长" → 在支持该功能的模型上使用
```
--extend-video
```
参数。
"将16:9视频转为竖版故事剪辑" → 运行
```
reframe-video --aspect-ratio 9:16
```
。
"将这段引语/标题动画化" → 不属此功能范围：moda-video-motion负责在画布上添加真实文字；模型会扭曲文字效果。

Errors

错误处理

Any typed error → load moda-core and read its recovery reference. 422 = a guessed parameter: re-read the model card and copy the value verbatim. Empty frames (

no_frames_decoded

) means Moda could not DECODE the file — never regenerate on it.

任何输入错误 → 加载moda-core并查阅其故障恢复文档。 422错误 = 参数猜测错误：重新阅读模型卡片并严格复制参数值。空帧（

no_frames_decoded

）表示Moda无法解码该文件——切勿基于此文件重新生成。

Make it recurring

实现定期生成

Pin the model and brand defaults for this repo → moda-context; a recurring product-clip cadence → moda-automate.

See also: moda-video — the lane fork, canvas motion, mp4/gif export · moda-core — the contract, recovery, everything Moda can do.

为当前仓库固定模型和品牌默认设置 → 使用moda-context；定期生成产品视频 → 使用moda-automate。

另请参阅：moda-video — 分支功能、画布动态效果、MP4/GIF导出 · moda-core — 协议、故障恢复、Moda所有功能说明。

References

参考文档

Doc	Load when
references/video.md	always — model strengths, knob rules, prompt craft, workflows
references/omni-and-media.md	metered-lane semantics, the best-of-N pattern, audio pairing

文档	查阅时机
references/video.md	随时查阅 — 模型优势、参数规则、提示词撰写、工作流程
references/omni-and-media.md	按使用量计费的语义说明、N选优模式、音频搭配