seedance-2-5-skill

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Seedance 2.5 Skill

Language route

语言路径

For an English request, follow this file and the
```
*.md
```
references.
For a Chinese request, read the Chinese workflow first, then use the matching
```
*.zh-CN.md
```
reference files.
Keep model IDs, JSON keys, commands, media placeholders, and native-audio symbols exactly as code. Do not translate them.

Do not force every request through one image-grid pipeline. Choose the video route first, then enable only the preparation modules the job needs.

对于英文请求，遵循本文件和
```
*.md
```
参考文件。
对于中文请求，先阅读中文工作流，然后使用匹配的
```
*.zh-CN.md
```
参考文件。
保持 model ID、JSON key、命令、媒体占位符和 native-audio 符号与代码中完全一致。不要翻译它们。

不要强制所有请求都走同一套 image-grid 流程。先选择视频路线，然后只启用任务需要的准备模块。

1. Choose the creative route

1. 选择创作路线

Need	Route	Inputs	Result
One short, simple scene	T2V	Text prompt	One self-contained shot
A multi-shot sequence with readable panels	R2V storyboard	One complete storyboard image	One request turns panel order into a continuous video
A clip controlled by people, product, scene, or style assets	R2V asset references	A small role-specific asset pack	One clip built from those references
A shot with an exact beginning and ending	I2V shot pair	Start and end keyframes	One independently reviewable shot
An uninterrupted action exceeding the supported duration	Extend / chain	Previous generated tail frame and next prompt	Continuation of the same shot
One continuous piece carrying several events	Staged whole-short	Text plus optional references	One request covering ordered stages, each landing on a stated end state
A scoped change to an existing video	Editing	Source video plus target references	The source with only the named region or element changed
A bridge between two finished clips	Seamless transition	Two videos	Generated bridge content between them
Motion, blocking, and camera taken from a 3D preview	Blockout reference	Coarse or fine blockout video plus look references	Final render following the blockout's timing and staging

Use Seedance 2.0 as the executable default. Offer a Seedance 2.5 whole-short route only when the selected provider exposes that model and its actual limits.

The last four routes depend on capabilities that differ per model and per provider. Verify availability before offering one; see capabilities for the 2.0/2.5 comparison and for which published capabilities are platform features rather than API parameters.

需求	路线	输入	结果
一个简短、简单的场景	T2V	文本提示词	一个自包含镜头
带有清晰可读分镜格的多镜头序列	R2V storyboard	一张完整的分镜图	一次请求将分镜格顺序转换为连续视频
由人物、产品、场景或风格素材控制的一段视频	R2V asset references	一组规模较小、角色明确的素材	一段根据这些参考素材构建的视频
需要精确起始和结束状态的镜头	I2V shot pair	起始和结束关键帧	一个可独立审查的镜头
超过支持时长的不间断动作	Extend / chain	上一段生成视频的尾帧和下一条提示词	同一镜头的延续
承载多个事件的连续作品	Staged whole-short	文本及可选参考素材	一次请求覆盖有序阶段，每个阶段都落在明确说明的结束状态上
对现有视频进行范围明确的修改	Editing	源视频和目标参考素材	仅修改指定区域或元素的源视频
在两段已完成视频之间建立衔接	Seamless transition	两段视频	在两者之间生成的过渡内容
从 3D 预览中获取运动、调度和镜头信息	Blockout reference	粗略或精细的 blockout 视频及外观参考素材	按照 blockout 的时序和调度完成最终渲染

将 Seedance 2.0 作为可执行的默认模型。只有当所选 provider 公开了 Seedance 2.5 模型及其实际限制时，才提供 Seedance 2.5 whole-short 路线。

最后四条路线依赖各模型和各 provider 不同的能力。提供这些路线前必须先验证可用性；有关 Seedance 2.0/2.5 的对比，以及哪些已发布能力属于平台功能而非 API 参数，请参阅能力说明。

Storyboard or individual keyframes

分镜图或独立关键帧

Use the whole storyboard image in one R2V request by default whenever individual panels remain visually readable. Do not crop it first. Seedance can interpret the ordered panels as one continuous multi-shot video.
Use I2V shot pairs only when independent reshoots or precise start/end states matter more than the transition quality of one R2V generation.
Do not upload every storyboard cell as a default R2V asset pack. Use several R2V images only when each has a distinct role, such as subject, product, setting, style, or motion reference.

只要各个分镜格仍然清晰可读，默认应在一次 R2V 请求中使用完整分镜图。不要预先裁切。Seedance 可以将有序分镜格理解为一个连续的多镜头视频。
仅当独立重拍或精确的起始与结束状态，比一次 R2V 生成的转场质量更重要时，才使用 I2V shot pair。
不要默认将每个分镜格作为 R2V asset pack 上传。只有当每张图承担不同角色时，才使用多张 R2V 图片，例如主体、产品、环境、风格或运动参考。

2. Enable only needed preparation

2. 只启用必要的准备模块

Subject brief

主体简报

Use this only for a person, product, prop, hand, vehicle, or scene that must recur. Record 3–5 invariants: silhouette or proportion, signature material or wardrobe, key colour, and any must-preserve marking. Skip it for a one-off atmosphere shot.

For a recurring person, make a clean face close-up and a separate full-body reference. Do not use a front/side/back composite as the identity input; it can be interpreted as multiple people. Multi-angle product references remain useful when the object itself must be shown from several sides.

仅当人物、产品、道具、手部、载具或场景需要反复出现时使用。记录 3–5 项不变量：轮廓或比例、标志性材质或服装、关键颜色，以及任何必须保留的标记。对于一次性氛围镜头则跳过。

对于反复出现的人物，制作一张干净的正脸特写和一张独立的全身参考图。不要使用正面/侧面/背面合成图作为身份输入；它可能会被理解为多个人。对于必须从多个角度展示的物体，多角度产品参考仍然有用。

Keyframes

关键帧

Create a start keyframe for every I2V shot. Add an end keyframe only when the shot must land on a specific action, composition, product pose, or hand position. Use one clean scene per keyframe.

为每个 I2V 镜头创建起始关键帧。仅当镜头必须落在特定动作、构图、产品姿态或手部位置时，才添加结束关键帧。每个关键帧使用一个干净场景。

Storyboard

分镜图

Use an existing storyboard directly as the R2V reference. Seedance normally understands panel order and does not require panel numbers, dividers, arrows, or notes to be removed in advance. Make a clean copy only after a test generation actually renders an unwanted divider, number, caption, or multi-panel layout.

When a multi-shot request has no storyboard, use the Seedream template in prompt templates to create one board. Display that board in the host UI, inspect it yourself, then continue to Seedance R2V when it passes review. Showing the board is a progress update, not a user-approval gate.

For a supplied storyboard, display it unless it is already visible in the conversation. Check planned order, readable key beats, recurring-subject consistency, and content-specific constraints such as anatomy, product form, or critical text. Refine a visibly failed board before video generation. Ask the user only when a creative choice cannot be inferred.

If the route deliberately changes to I2V shot pairs, crop panels only then. Inspect the layout first: automatic crops can verify position, not whether the image model drew the intended panel layout.

默认直接使用现有分镜图作为 R2V reference。Seedance 通常能够理解分镜格顺序，不要求事先移除分镜格编号、分隔线、箭头或注释。只有在测试生成确实渲染出不想要的分隔线、编号、字幕或多面板布局后，才制作干净副本。

多镜头请求没有分镜图时，使用提示词模板中的 Seedream 模板创建一块分镜板。 在宿主 UI 中展示该分镜板并自行检查，通过审查后再继续执行 Seedance R2V。 展示分镜板只是进度更新，不是用户审批关卡。

对于用户提供的分镜图，除非它已在对话中可见，否则先展示输入。检查规划顺序、清晰可读的关键节拍、反复出现的主体一致性，以及与内容相关的约束，例如人体结构、产品形态或关键文字。若分镜图明显不合格，应先优化后再生成视频。仅当无法推断创作选择时才询问用户。

如果路线有意改为 I2V shot pair，此时才裁切分镜格。先检查布局：自动裁切可以验证位置，但不能验证图像模型是否绘制了预期的分镜格布局。

3. Design continuity and cuts

3. 设计连续性和剪辑点

First-and-last frames control one shot; they do not mean every shot must inherit the prior clip's tail.

Transition	Use prior tail as next start?	Design rule
One uninterrupted action	Yes	Generate in sequence and inspect the seam
Hard cut to a new angle, place, product, or time	No	Design each shot independently
Match cut	Usually no	Match movement direction, shape, colour, or composition
Occlusion or whip transition	No	End with the occluding action; start the next shot inside or after it
Insert or cutaway	No	Use an object, environment, or product detail as a bridge

Put important cuts, matches, and occlusions in the storyboard and prompt. Do not rely on a cross-dissolve to repair unrelated shots.

首尾帧只控制一个镜头；这并不意味着每个镜头都必须继承上一段视频的尾帧。

转场	是否将上一段尾帧作为下一段起点？	设计规则
一个不间断的动作	是	按顺序生成并检查接缝
硬切到新角度、新地点、新产品或新时间	否	每个镜头独立设计
匹配剪辑	通常否	匹配运动方向、形状、颜色或构图
遮挡或甩镜转场	否	以上遮挡动作结束；在遮挡内部或之后开始下一镜头
插入镜头或切出镜头	否	使用物体、环境或产品细节作为衔接

将重要剪辑点、匹配关系和遮挡安排在分镜图与提示词中。不要依赖交叉叠化来修复互不相关的镜头。

4. Write the video prompt

4. 编写视频提示词

Scope: put each instruction where it applies

范围：把每条指令放在适用的位置

Before writing blocks, sort what you know by what it governs. Instructions in the wrong place are the most common cause of drift — a global rule written inside beat 1 stops applying at beat 4.

Scope	Governs	Contents
Global	The whole piece	Film type, scene, style, one-sentence premise, camera principle
Locks	Anything that must not drift	Identity, reference roles, audio source, continuity, negatives
Time	One beat or stage	Stage events and their end states

Restate the two or three most expensive locks at the physical end of the prompt; recency helps. That is a placement convention, not a fourth scope — the content still belongs to Locks and appears there first.

This mirrors the model-agnostic spec format in the Universal Video Prompt Skill. Use that skill when one brief has to run on more than one model; use this file for Seedance-specific writing. This is a required companion for a complete Seedance 2.5 Skill setup. If the link does not resolve, help the user install

universal-video-prompt-skill

before continuing; do not invent the missing shared specification.

编写 block 前，先按“它约束什么”对已知信息进行归类。指令放错位置是发生漂移最常见的原因——写在 beat 1 里的 global rule 到 beat 4 就不再适用。

范围	约束对象	内容
Global	整个作品	影片类型、场景、风格、一句话前提、运镜原则
Locks	任何不得发生漂移的内容	身份、参考素材角色、音频来源、连续性、负向约束
Time	一个 beat 或 stage	阶段事件及其结束状态

在提示词的物理末尾重申代价最高的两三个 lock；越靠近末尾越有帮助。这只是一种放置约定，不是第四种 scope——这些内容仍属于 Locks，并且应先在那里出现。

这与 Universal Video Prompt Skill 中的模型无关规范格式一致。当同一份 brief 需要在多个模型上运行时，使用该 skill；针对 Seedance 的写作则使用本文件。要构成完整的 Seedance 2.5 Skill 设置，该 skill 是必需的配套项。如果链接无法解析，应先帮助用户安装

universal-video-prompt-skill

再继续；不要自行编造缺失的共享规范。

Blocks

Block

Use only the blocks that affect the shot:

text

[subject/reference binding]
+ [one observable action]
+ [space and important object relationships]
+ [one primary camera move, coherent composite move, or a cut]
+ [light/style when it matters]
+ [audio or dialogue when enabled]
+ [end state, for any stage that must land somewhere specific]
+ [must-preserve constraints]

只使用会影响该镜头的 block：

text

[subject/reference binding]
+ [one observable action]
+ [space and important object relationships]
+ [one primary camera move, coherent composite move, or a cut]
+ [light/style when it matters]
+ [audio or dialogue when enabled]
+ [end state, for any stage that must land somewhere specific]
+ [must-preserve constraints]

End states carry multi-event work

结束状态承载多事件内容

For anything with more than one event, state what is visibly true when each stage ends. This is the highest-leverage single addition to a multi-stage prompt: it converts "keep it consistent" into something the model can target and you can check.

text

weak:   the two of them keep working on the bouquet
strong: end state: the florist holds the bouquet in the left hand;
        the scissors are back on the right side of the bench

An end state must be visible. "She feels relieved" is not one; "her shoulders drop and the frown clears" is. Read long video for the staged structure in full.

对于包含多个事件的任何内容，都要说明每个 stage 结束时哪些内容在视觉上成立。对于多阶段提示词，这是收益最高的单项补充：它能把“保持一致”转化为模型可以瞄准、你也可以核查的目标。

text

weak:   the two of them keep working on the bouquet
strong: end state: the florist holds the bouquet in the left hand;
        the scissors are back on the right side of the bench

结束状态必须可见。“她感到如释重负”不是一个结束状态；“她的肩膀放松，皱眉消失”才是。完整的分阶段结构请阅读长视频。

Time granularity: decide before writing beats

时间粒度：编写 beat 前先做决定

Granularity is a prior decision. Writing beats at second precision and then downgrading means rewriting them.

Granularity	Use when
None — event order only	One continuous action, mood pieces, single shots. Timestamps here fragment the shot
Stages + end states	Most narrative work. Default
Second-level	Only under an external hard constraint: music, lip sync, reference handoff, a beat that must land at a fixed time

Infer it when the input settles it — a supplied music or voiceover track means second-level, a stated mood piece means none, an explicit fixed beat means second-level. When the request is a multi-event narrative with no external constraint, ask, and recommend with a reason rather than presenting a bare menu.

Timestamps allocate a time budget; they are not frame-accurate edit points, and actions may land slightly before or after a boundary. Do not demand impossible density such as three distinct actions inside one second.

Name reference roles explicitly, for example

Image 1: person

Image 2: product

Image 3: kitchen setting

For multi-shot R2V, list
```
Shot 1
```
,
```
Shot 2
```
, and
```
Shot 3
```
in event order. Set duration in provider controls rather than forcing exact seconds in text.
Prefer one primary movement per shot. A composite movement is valid when its direction, relation to the subject, and speed express one synchronized intent.
When native audio is enabled, use
```
（）
```
for music,
```
<>
```
for sound effects,
```
{}
```
for dialogue, and
```
【】
```
for on-screen captions.
State only constraints that are costly to redo.

Read the reference matching the job:

File	Read it for
prompt templates	Route-specific templates
prompt blocks	Reusable camera, audio, constraint patterns
long video	Staged structure, end states, timestamp rules
multi reference	Binding many assets without confusing them
real person	Believable human subjects, and when to omit the detail
transitions	Which transitions to generate and which to edit
editing and extension	Changing or continuing existing video
capabilities	2.0 vs 2.5 limits; platform features vs API parameters
model profile	Measured per-model behaviour and compile notes
cinematography	Detailed visual decisions
troubleshooting	Fault-specific fixes
execution adapters	Runner and adapter configuration

粒度是前置决策。先以秒级精度编写 beat，然后再降低粒度，就意味着必须重写。

粒度	使用场景
无——仅事件顺序	一个连续动作、氛围片段、单镜头。此处使用时间戳会割裂镜头
阶段 + 结束状态	大多数叙事工作。默认
秒级	仅在存在外部硬性约束时使用：音乐、口型同步、参考素材交接，或必须落在固定时间的 beat

当输入已经确定粒度时，可据此推断——提供音乐或旁白音轨意味着使用秒级，明确的氛围片段意味着不使用时间粒度，指定固定节拍意味着使用秒级。当多事件叙事请求没有外部约束时，应询问用户并给出有理由的建议，而不是只提供一份裸菜单。

时间戳用于分配时间预算，并不是帧级精确的剪辑点；动作可能会略微早于或晚于边界落下。不要要求不可能的密度，例如在一秒内完成三个不同的动作。

明确命名参考素材角色，例如

Image 1: person

、

Image 2: product

、

Image 3: kitchen setting

。

对于多镜头 R2V，按事件顺序列出
```
Shot 1
```
、
```
Shot 2
```
和
```
Shot 3
```
。在 provider 控件中设置时长，不要在文本中强制指定精确秒数。
每个镜头优先使用一个主要运镜。当复合运镜的方向、与主体的关系和速度共同表达一个同步意图时，这种用法是有效的。
启用 native audio 时，使用
```
（）
```
表示音乐、
```
<>
```
表示音效、
```
{}
```
表示对白，使用
```
【】
```
表示屏幕字幕。
只写出重做成本高昂的约束。

阅读与任务匹配的参考文件：

文件	用途
提示词模板	路线专用模板
提示词 Block	可复用的运镜、音频和约束模式
长视频	分阶段结构、结束状态、时间戳规则
多参考素材	在不混淆素材的情况下绑定多个资产
真人	可信的人物主体，以及何时省略细节
转场	哪些转场应生成，哪些应通过编辑完成
编辑与扩展	修改或延续现有视频
能力说明	Seedance 2.0 与 2.5 的限制；平台功能与 API 参数
模型档案	实测的各模型行为和编译说明
电影摄影	详细的视觉决策
故障排查	针对具体故障的修复方法
执行适配器	Runner 和 adapter 配置

5. Generate, review, and finish

5. 生成、审查与收尾

For a generated storyboard, create only the still first, display it in the conversation, and inspect it before any video request.
For a supplied storyboard, display the input unless it is already visible, then verify it fits the chosen route.
If the board passes review, generate one representative video pass without waiting for approval. Otherwise refine or regenerate the board first.
Review identity, locks, stage end states, composition, motion, seam, and audio in that order, and stop at the first failure — later checks are wasted effort on a wrong identity. Regenerate only the failed shot or segment.
Generate chains in order because the next segment needs the real prior tail. Generate cut-based clips independently and edit the planned transition.

The bundled script is a draft assembler, not a colour-grading or music-mixing system.

对于生成的分镜图，先只创建静帧，在对话中展示并检查，然后再发起任何视频请求。
对于用户提供的分镜图，除非已经可见，否则先展示输入，然后验证它是否适合所选路线。
如果分镜图通过审查，无需等待用户批准，即执行一次代表性视频生成。否则先优化或重新生成分镜图。
依次审查身份、lock、stage 结束状态、构图、运动、接缝和音频，并在首次失败处停止——如果身份已经错误，后续检查都是在浪费精力。只重新生成失败的镜头或片段。
按顺序生成链式片段，因为下一段需要真实的上一段尾帧。基于硬切的片段应独立生成，并编辑规划的转场。

内置脚本是草稿组装器，不是调色或音乐混音系统。

Atlas execution layer

Atlas 执行层

Keep creative route selection independent from how a job is submitted. The default models are Seedream 5.0 Pro for stills and Seedance 2.0 for video; users may override them only after verifying route support.

In an agent conversation, use the Atlas Cloud Skill as the default direct generation route. It can discover a model, upload local media, submit an image or video request, poll, and retrieve outputs. Report

Execution: atlas-skill

only when it actually submitted the generation.

Use

atlas-mcp

only when the user explicitly selects MCP and its generation tools are exposed. Use

atlas-cli

only when the user explicitly selects a terminal, script, CI, or batch run. If the Atlas Cloud Skill is missing, help install

AtlasCloudAI/atlas-cloud-skills

before selecting a fallback.

Before reporting that an Atlas Cloud API key is missing, check the credentials in the selected execution process. For the REST runner, check

ATLASCLOUD_API_KEY

first and

ATLAS_CLOUD_API_KEY

as a compatibility alias. Do not infer credential availability from a different provider, plugin, or process; each execution channel can have an independent credential scope.

If neither key exists, direct the user to

https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=awesome-seedance-2.5-prompts-skills

. Never ask them to paste the key in chat. Tell them to set

ATLASCLOUD_API_KEY

in the submitting process or the host's secure environment settings, then refresh or restart the execution session if needed. If the key exists in a parent or host configuration but is absent from the submitting process, report an environment-scope mismatch instead of saying the user has no key.

让创作路线选择与任务提交方式保持独立。静态图的默认模型是 Seedream 5.0 Pro，视频的默认模型是 Seedance 2.0；只有验证路线支持后，用户才能覆盖这些模型。

在 Agent 对话中，默认使用 Atlas Cloud Skill 作为直接生成路线。它可以发现模型、上传本地媒体、提交图片或视频请求、轮询并检索输出。只有实际提交了生成任务时，才报告

Execution: atlas-skill

。

仅当用户明确选择 MCP 且其生成工具已暴露时，才使用

atlas-mcp

。仅当用户明确选择终端、脚本、CI 或批处理运行时，才使用

atlas-cli

。如果缺少 Atlas Cloud Skill，应先帮助安装

AtlasCloudAI/atlas-cloud-skills

，再选择 fallback。

在报告 Atlas Cloud API key 缺失之前，检查所选执行进程中的凭据。对于 REST runner，先检查

ATLASCLOUD_API_KEY

，并将

ATLAS_CLOUD_API_KEY

作为兼容别名检查。不要根据其他 provider、plugin 或进程推断凭据可用性；每个执行通道都可以有独立的凭据作用域。

如果两个 key 都不存在，引导用户前往

https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=awesome-seedance-2.5-prompts-skills

。绝不要让用户在聊天中粘贴 key。告诉他们应在提交进程中或宿主的 secure environment settings 中设置

ATLASCLOUD_API_KEY

，然后根据需要刷新或重启执行会话。如果 key 存在于父级或宿主配置中，但提交进程中不存在，应报告环境作用域不匹配，而不是说用户没有 key。

Billable task state machine

计费任务状态机

Apply these rules to every image and video generation:

After submission, record the prediction ID and logical stage immediately.
Treat
```
starting
```
,
```
queued
```
,
```
pending
```
, and
```
processing
```
as active. Poll the same ID every 2 seconds; never submit another task for that stage.
Treat
```
completed
```
and
```
succeeded
```
as successful terminal states. Download and inspect the output before starting a dependent stage.
Treat
```
failed
```
,
```
timeout
```
, and
```
canceled
```
as terminal failures. A new task requires an explicit retry decision; report the old ID and possible extra cost first.
A zero or missing processing-time field, delayed output, a local polling timeout, a stopped turn, or a temporary status-query error is not proof of failure. Preserve the ID and resume polling.
Interpret
```
continue
```
as “resume the existing task,” never as permission to retry. Do not submit video while its required storyboard is still active.

The 2-second interval applies to every Atlas execution route in this workflow. For

atlas-skill

, repeat its prediction-result step with the same ID. For

atlas-mcp

, call

atlas_get_prediction

with the same ID every 2 seconds. The MCP server performs a single status lookup per tool call; the agent owns the loop. The bundled REST and CLI adapters enforce the interval in code. A status lookup is read-only and must never be replaced with another generation call.

When the runner must resume, set

execution.resumePredictionIds.<stage>

to the existing ID. Supported stage keys include

grid

ref1

ref2

seg1

shot1

, and

clip1

. Never create a replacement merely because a prior polling process ended.

scripts/generate.mjs

cannot invoke an agent Skill or MCP server. It is a separate batch runner: it defaults to

atlas-rest

, and can use

atlas-cli

only when explicitly set in

execution.adapter

. It never selects CLI automatically. See execution adapters.

bash

undefined

对每次图片和视频生成都应用以下规则：

提交后，立即记录 prediction ID 和逻辑 stage。
将
```
starting
```
、
```
queued
```
、
```
pending
```
和
```
processing
```
视为活动状态。每 2 秒轮询同一个 ID；绝不要为该 stage 再次提交任务。
将
```
completed
```
和
```
succeeded
```
视为成功的终止状态。在开始依赖阶段之前，下载并检查输出。
将
```
failed
```
、
```
timeout
```
和
```
canceled
```
视为终止失败。新任务需要明确的重试决定；先报告旧 ID 和可能产生的额外费用。
processing-time 字段为零或缺失、输出延迟、本地轮询超时、本轮执行停止或临时状态查询错误，都不是失败证据。保留 ID 并恢复轮询。
将
```
continue
```
解释为“恢复现有任务”，绝不能理解为允许重试。所需 storyboard 仍处于活动状态时，不要提交视频。

2 秒间隔适用于本工作流中的每条 Atlas 执行路线。对于

atlas-skill

，使用同一个 ID 重复执行 prediction-result 步骤。对于

atlas-mcp

，每 2 秒使用同一个 ID 调用

atlas_get_prediction

。MCP server 每次工具调用只执行一次状态查询；轮询循环由 Agent 控制。内置 REST 和 CLI adapter 在代码中强制执行该间隔。状态查询是只读操作，绝不能替换为另一次生成调用。

runner 必须恢复时，将

execution.resumePredictionIds.<stage>

设置为现有 ID。支持的 stage key 包括

grid

、

ref1

、

ref2

、

seg1

、

shot1

和

clip1

。仅仅因为先前的轮询进程结束，绝不能创建替代任务。

scripts/generate.mjs

不能调用 Agent Skill 或 MCP server。它是一个独立的批处理 runner：默认为

atlas-rest

，只有当

execution.adapter

中明确设置时才能使用

atlas-cli

。它绝不会自动选择 CLI。参见执行适配器。

bash

undefined

Generate a storyboard only. The runner prints [storyboard-preview] with an

absolute path; display and inspect that image before starting video work.

GRID_ONLY=1 node scripts/generate.mjs scripts/myjob.json

Run only the first independent clip or segment as a quality gate.

CLIPS_MAX=1 node scripts/generate.mjs scripts/myjob.json SEGS_MAX=1 node scripts/generate.mjs scripts/myjob.json


```json
{ "execution": { "adapter": "atlas-cli" } }

Available runner modes:

```
grid
```
: crop a model storyboard and make one independent I2V clip per panel; suitable for a hard-cut montage.
```
shot-pairs
```
: make independent I2V shots from
```
segments[]
```
, with a
```
first
```
and optional
```
last
```
keyframe index.
```
reference
```
: send a small role-specific set of R2V references. A reference may be generated from a prompt or read from a local file.
```
chain
```
: continue one action by feeding the generated tail frame to the next segment. It is an alignment aid, not a guarantee of an invisible seam.

For fault-specific fixes, read troubleshooting.

CLIPS_MAX=1 node scripts/generate.mjs scripts/myjob.json SEGS_MAX=1 node scripts/generate.mjs scripts/myjob.json


```json
{ "execution": { "adapter": "atlas-cli" } }

可用的 runner 模式：

```
grid
```
：裁切模型生成的分镜图，并为每个分镜格制作一个独立的 I2V 片段；适合硬切蒙太奇。
```
shot-pairs
```
：根据
```
segments[]
```
制作独立的 I2V 镜头，其中包含
```
first
```
和可选的
```
last
```
关键帧索引。
```
reference
```
：发送一组规模较小、角色明确的 R2V 参考素材。参考素材既可以通过 prompt 生成，也可以从本地文件读取。
```
chain
```
：将生成的尾帧作为下一片段的输入，以延续一个动作。它是一种对齐辅助手段，并不保证接缝不可见。

有关针对具体故障的修复方法，请阅读故障排查。