wan-2-7

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Wan 2.7 — Pro Pack on RunComfy

Wan 2.7 — RunComfy专业版套件

runcomfy.com · Text-to-video · GitHub

Wan-AI's Wan 2.7 — flagship video model with multi-reference conditioning and audio-driven lip-sync — hosted on the RunComfy Model API.

bash

npx skills add agentspace-so/runcomfy-skills --skill wan-2-7 -g

runcomfy.com · 文本转视频 · GitHub

Wan-AI的Wan 2.7——具备多参考条件控制和音频驱动唇形同步功能的旗舰视频模型，托管于RunComfy模型API。

bash

npx skills add agentspace-so/runcomfy-skills --skill wan-2-7 -g

When to pick this model (vs siblings)

何时选择该模型（对比同类模型）

You want	Use
Lip-sync video to an audio track you supply	Wan 2.7 ( `audio_url` )
Multi-reference fine motion control	Wan 2.7
Smooth transitions, accurate motion physics	Wan 2.7
Currently-#1 blind-vote video model	HappyHorse 1.0
Multi-modal cinematic with image+video+audio refs + in-pass voice generation	Seedance 2.0 Pro
Cinematic motion editing on existing footage	Kling Video O1
Ultra-fast iteration	LTX 2

If the user said "Wan" / "Wan 2.7" / "wan-ai" / "alibaba video" explicitly, route here regardless.

需求场景	推荐模型
将视频与你提供的音频轨道进行唇形同步	Wan 2.7（使用 `audio_url` ）
多参考精细化运动控制	Wan 2.7
流畅转场、精准运动物理效果	Wan 2.7
当前盲投排名第一的视频模型	HappyHorse 1.0
多模态电影级效果，支持图片+视频+音频参考+内置语音生成	Seedance 2.0 Pro
对现有素材进行电影级运动编辑	Kling Video O1
超快速迭代生成	LTX 2

如果用户明确提到"Wan" / "Wan 2.7" / "wan-ai" / "alibaba video"，无论其他条件如何，均选择此模型。

Prerequisites

前置条件

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy account —
```
runcomfy login
```
opens a browser device-code flow.
CI / containers — set
```
RUNCOMFY_TOKEN=<token>
```
instead of
```
runcomfy login
```
.

RunComfy CLI — 执行
```
npm i -g @runcomfy/cli
```
安装
RunComfy账号 — 执行
```
runcomfy login
```
会打开浏览器设备码登录流程
CI/容器环境 — 设置环境变量
```
RUNCOMFY_TOKEN=<token>
```
替代
```
runcomfy login
```
操作

Endpoints + input schema

接口及输入规范

wan-ai/wan-2-7/text-to-video

wan-ai/wan-2-7/text-to-video

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Up to ~5000 chars / ~1500 tokens.
`audio_url`	string	no	—	WAV/MP3, 3–30s, ≤15MB. Drives lip-sync. Omit → background music auto-generated.
`aspect_ratio`	enum	no	`16:9`	`16:9` , `9:16` , `1:1` , `4:3` , `3:4` .
`resolution`	enum	no	`1080p`	`720p` or `1080p` .
`duration`	enum	no	`5`	2–15 (whole seconds).
`negative_prompt`	string	no	—	Up to 500 chars. Concrete issues to avoid.
`enable_prompt_expansion`	bool	no	true	Auto-rewrites short prompts. Disable for literal control.
`seed`	int	no	—	0..2^31-1. Reuse for variants.

字段	类型	是否必填	默认值	说明
`prompt`	字符串	是	—	最多约5000字符/1500tokens
`audio_url`	字符串	否	—	WAV/MP3格式，时长3–30秒，文件≤15MB。用于驱动唇形同步。若省略则自动生成背景音乐
`aspect_ratio`	枚举值	否	`16:9`	可选值： `16:9` , `9:16` , `1:1` , `4:3` , `3:4`
`resolution`	枚举值	否	`1080p`	可选值： `720p` 或 `1080p`
`duration`	枚举值	否	`5`	取值范围2–15（整数秒）
`negative_prompt`	字符串	否	—	最多500字符，用于指定需要避免的具体问题
`enable_prompt_expansion`	布尔值	否	true	自动重写简短提示词。若需严格按字面生成则禁用此选项
`seed`	整数	否	—	取值范围0..2^31-1。重复使用可生成同主题变体内容

How to invoke

调用方式

Default (5s 1080p 16:9, prompt-expanded):

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{"prompt": "<user prompt>"}' \
  --output-dir <absolute/path>

Audio-driven lip-sync (your own track):

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{
    "prompt": "Medium close-up of the spokesperson, warm key light, locked tripod, slight breathing motion.",
    "audio_url": "https://.../voiceover.mp3",
    "duration": 12,
    "aspect_ratio": "9:16"
  }' \
  --output-dir <absolute/path>

Literal control (no auto-expansion):

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{
    "prompt": "<exactly what you want, verbatim>",
    "enable_prompt_expansion": false,
    "negative_prompt": "no subtitles, no flicker, no distorted hands"
  }' \
  --output-dir <absolute/path>

默认配置（5秒1080p 16:9，启用提示词扩展）：

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{"prompt": "<用户提示词>"}' \
  --output-dir <绝对路径>

音频驱动唇形同步（使用自定义音频轨道）：

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{
    "prompt": "发言人的中近景镜头，暖色调主光源，固定三脚架，轻微呼吸动作",
    "audio_url": "https://.../voiceover.mp3",
    "duration": 12,
    "aspect_ratio": "9:16"
  }' \
  --output-dir <绝对路径>

严格字面控制（禁用自动扩展）：

bash

runcomfy run wan-ai/wan-2-7/text-to-video \
  --input '{
    "prompt": "<完全按你想要的字面内容>",
    "enable_prompt_expansion": false,
    "negative_prompt": "无字幕，无闪烁，无手部变形"
  }' \
  --output-dir <绝对路径>

Prompting — what actually works

提示词技巧——有效方法

Camera + motion in plain English. "Slow dolly in", "locked tripod, low angle", "handheld follow", "crane move from above". Front-load the shot.

One primary action per clip. Don't pile up multiple competing actions. Pick the beat: "she turns, then smiles" not "she turns AND smiles AND a bus passes AND...".

Use
negative_prompt
for concrete issues. Good: "no subtitles, no watermark, no flicker". Bad (vague): "no bad lighting".

Prompt expansion is on by default. Short prompts get auto-rewritten by the model. For terse / literal prompts (e.g. brand-strict ad copy), disable with

enable_prompt_expansion: false

Audio specs matter.

audio_url

must be 3–30s, ≤15MB, WAV/MP3. Out-of-range files reject. Match audio length to clip duration.

Iterate seeds. Reuse the same seed when you want consistent output across variants of the same prompt. Change seed for genuine variety.

Anti-patterns:

Static-frame descriptions → motion will be vague.
Vague negatives ("no bad colors") → ignored.
Audio outside the 3–30s / 15MB / WAV-MP3 spec → rejected.
Prompts > 5000 chars / 1500 tokens → degraded output.

用直白英文描述镜头与运动。比如"Slow dolly in"（缓慢推镜头）、"locked tripod, low angle"（固定三脚架，低角度）、"handheld follow"（手持跟拍）、"crane move from above"（从上方吊臂拍摄）。将镜头描述放在提示词开头。

每个片段聚焦一个核心动作。不要堆砌多个冲突动作。选择关键帧：比如"她转身，然后微笑"而非"她转身且微笑同时有公交车经过……"。

用
negative_prompt
指定具体问题。正确示例："无字幕，无水印，无闪烁"。错误示例（模糊描述）："无糟糕光线"。

默认启用提示词扩展。简短提示词会被模型自动重写。若需简洁/严格符合字面的提示词（如品牌严格要求的广告文案），请设置

enable_prompt_expansion: false

禁用此功能。

音频规格很重要。

audio_url

必须是3–30秒、≤15MB的WAV/MP3文件。超出范围的文件会被拒绝。音频时长需与视频片段时长匹配。

迭代种子值。当你希望同一提示词的变体输出保持一致性时，重复使用相同的seed值。更换seed值可生成完全不同的内容。

反模式：

静态画面描述→运动效果会模糊不清
模糊的负面提示词（如"无糟糕色彩"）→会被忽略
超出3–30秒/15MB/WAV-MP3规格的音频→会被拒绝
超过5000字符/1500tokens的提示词→输出质量下降

Where it shines

优势场景

Use case	Why Wan 2.7
Lip-synced ads with custom voiceover	`audio_url` accepts your track
Multi-language dub variants	Same prompt, different `audio_url` per language
Multi-reference motion control	Up to 5 reference media (image / video / voice)
Smooth transitions + motion physics	Strong physics-aware motion priors
Negative-prompted clean output	Targeted issue exclusion

使用场景	Wan 2.7的优势
带自定义旁白的唇形同步广告	`audio_url` 支持导入自定义音频轨道
多语言配音变体	同一提示词，为不同语言搭配不同 `audio_url` 即可
多参考运动控制	最多支持5种参考媒体（图片/视频/语音）
流畅转场+运动物理效果	具备强大的物理感知运动先验模型
通过负面提示词生成纯净输出	可精准排除指定问题

Sample prompts (verified to produce strong results)

验证有效的示例提示词

Page example (product showcase):

Cinematic medium shot of a product on a marble surface, soft studio
lighting, slow subtle camera push-in, shallow depth of field, premium
commercial look, crisp 1080p detail

Lip-synced spokesperson (with
audio_url
):

Medium close-up of a confident spokesperson in a softly-lit recording
booth, leaning slightly toward the camera, locked tripod, shallow depth
of field, warm key light from camera-left.

Vertical platform-native:

9:16 vertical short. A barista pulls a single espresso shot, steam
rising into morning sun, rich crema slowly forming. Close-up handheld,
shallow DOF, warm cafe ambience.

产品展示示例：

大理石台面上产品的电影级中景镜头，柔和的工作室灯光，缓慢轻微的镜头推进，浅景深，高端商业风格，清晰的1080p细节

唇形同步发言人（搭配
audio_url
）：

柔和灯光录音棚中自信发言人的中近景镜头，微微倾向镜头，固定三脚架，浅景深，镜头左侧的暖色调主光源

垂直平台原生内容：

9:16竖版短视频。咖啡师萃取浓缩咖啡，蒸汽融入晨光，浓郁的油脂慢慢形成。手持近景拍摄，浅景深，温馨的咖啡馆氛围

Limitations

局限性

Duration cap 15s. For longer narratives, stitch multiple calls.
No native 4K — 1080p ceiling.
Aspect ratios — only the 5 documented values.
Audio specs — 3–30s, ≤15MB, WAV/MP3 only.
Reference media cap 5 (image + video + voice combined).
For in-pass voice generation (no separate audio track), use Seedance 2.0 Pro — Wan accepts audio rather than generating it.

时长上限15秒。如需更长叙事内容，需拼接多次调用结果
无原生4K支持——最高分辨率为1080p
宽高比限制——仅支持文档中列出的5种取值
音频规格限制——仅支持3–30秒、≤15MB的WAV/MP3格式
参考媒体上限5个（图片+视频+语音总和）
如需内置语音生成（无需单独音频轨道），请使用Seedance 2.0 Pro——Wan仅支持导入音频，不具备语音生成功能

Exit codes

退出码

code	meaning
0	success
64	bad CLI args
65	bad input JSON / schema mismatch
69	upstream 5xx
75	retryable: timeout / 429
77	not signed in or token rejected

Full reference: docs.runcomfy.com/cli/troubleshooting.

代码	含义
0	成功
64	CLI参数错误
65	输入JSON错误/规格不匹配
69	上游服务5xx错误
75	可重试：超时/429请求过多
77	未登录或令牌被拒绝

完整参考：docs.runcomfy.com/cli/troubleshooting

How it works

工作原理

The skill invokes

runcomfy run wan-ai/wan-2-7/text-to-video

with a JSON body matching the schema. The CLI POSTs to

https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-7/text-to-video

, polls the request, fetches the result, and downloads any

.runcomfy.net

.runcomfy.com

URL into

--output-dir

Ctrl-C

cancels the remote request before exit.

该技能调用

runcomfy run wan-ai/wan-2-7/text-to-video

并传入符合规格的JSON参数。CLI会向

https://model-api.runcomfy.net/v1/models/wan-ai/wan-2-7/text-to-video

发送POST请求，轮询请求状态，获取结果，并将

.runcomfy.net

.runcomfy.com

域名下的生成文件下载到

--output-dir

指定路径。按

Ctrl-C

会在退出前取消远程请求。

Security & Privacy

安全与隐私

Token storage:
```
runcomfy login
```
writes the API token to
```
~/.config/runcomfy/token.json
```
with mode 0600 (owner-only read/write). Set
```
RUNCOMFY_TOKEN
```
env var to bypass the file entirely in CI / containers.
Input boundary: the user prompt is passed as a JSON string to the CLI via
```
--input
```
. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.
Third-party content: image / mask / video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit / video-edit model.
Outbound endpoints: only
```
model-api.runcomfy.net
```
(request submission) and
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
(download whitelist for generated outputs). No telemetry, no callbacks.
Generated-file size cap: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.

令牌存储：
```
runcomfy login
```
会将API令牌写入
```
~/.config/runcomfy/token.json
```
，权限设置为0600（仅所有者可读写）。在CI/容器环境中可设置
```
RUNCOMFY_TOKEN
```
环境变量，完全跳过文件存储步骤。
输入边界：用户提示词通过
```
--input
```
以JSON字符串形式传递给CLI。CLI不会对提示词进行shell扩展，而是直接通过HTTPS将JSON内容传输给模型API。提示词内容不存在shell注入风险。
第三方内容：你传入的图片/遮罩/视频URL由RunComfy模型服务器获取，而非本地CLI获取。请将外部URL视为不可信内容；基于图片的提示词注入是所有图片编辑/视频编辑模型的已知风险。
出站接口：仅与
```
model-api.runcomfy.net
```
（提交请求）和
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
（生成结果下载白名单）通信。无遥测数据，无回调操作。
生成文件大小限制：CLI会中止任何超过2GiB的单个文件下载，防止恶意或异常模型输出占满磁盘空间。

wan-2-7

Original

Translation

Wan 2.7 — Pro Pack on RunComfy

Wan 2.7 — RunComfy专业版套件

When to pick this model (vs siblings)

何时选择该模型（对比同类模型）

Prerequisites

前置条件

Endpoints + input schema

接口及输入规范

`wan-ai/wan-2-7/text-to-video`

`wan-ai/wan-2-7/text-to-video`

How to invoke

调用方式

Prompting — what actually works

提示词技巧——有效方法

Where it shines

优势场景

Sample prompts (verified to produce strong results)

验证有效的示例提示词

Limitations

局限性

Exit codes

退出码

How it works

工作原理

Security & Privacy

安全与隐私