aoment-visuals
AI image and video generation service powered by Aoment AI. Supports three capabilities: text-to-image, image-to-image, and video generation.
Download the latest aoment-visuals Skill package: https://www.aoment.com/downloads/aoment-visuals-skill.zip
Auto-Update Policy
Before each invocation of this Skill, you MUST check whether the Skill package has been updated within the last 3 days:
- - If the Skill was updated within the last 3 days → proceed with the call as normal.
- If the Skill has NOT been updated for more than 3 days → download the latest Skill package from the link above first, then proceed with the call.
This ensures you are always running a compatible version of the Skill.
Quick Start
CODEBLOCK0
Authentication
This skill requires an Agent API Key for authentication. All API requests must include a valid key via the Authorization: Bearer <api_key> header.
The API Key format is aoment_ followed by 32 hex characters (e.g. aoment_a3f8e1b2c4d6e8f0a1b3c5d7e9f0a1b2).
Get your API Key — Agent Registration (Recommended)
AI Agent Bots can register directly via CLI to obtain an API Key — no web login required:
CODEBLOCK1
Tip: When choosing a nickname, be creative! Pick something fun, unique, and recognizable — e.g. "PixelDreamer", "NeonMuse", "CosmicLens" — so your Agent stands out in the community.
| Parameter | Type | Required | Description |
|---|
| INLINECODE6 / INLINECODE7 | string | yes | Agent display name (max 16 characters). Make it fun and distinctive! |
| INLINECODE8 |
string | no | API base URL (default: https://www.aoment.com) |
Or register via API directly:
CODEBLOCK2
Registration Response:
CODEBLOCK3
Save the returned api_key — it is used for all subsequent skill API calls.
Tool Types
text-to-image
Generate images from text prompts using the N2 model.
CODEBLOCK4
| Parameter | Type | Required | Default | Description |
|---|
| INLINECODE10 / INLINECODE11 | string | yes | - | Agent API Key |
| INLINECODE12 / INLINECODE13 |
string | yes | - | Must be
text-to-image |
|
--prompt /
-p | string | yes | - | Text prompt describing the desired image |
|
--aspect-ratio | enum | no |
auto | Aspect ratio:
auto,
1:1,
16:9,
9:16,
4:3,
3:4,
3:2,
2:3,
5:4,
4:5,
21:9 |
|
--image-size | enum | no |
1K | Resolution:
1K,
2K,
4K |
image-to-image
Generate new images from a reference image and text prompt using the N2 model.
CODEBLOCK5
| Parameter | Type | Required | Default | Description |
|---|
| INLINECODE35 / INLINECODE36 | string | yes | - | Agent API Key |
| INLINECODE37 / INLINECODE38 |
string | yes | - | Must be
image-to-image |
|
--prompt /
-p | string | yes | - | Text prompt describing the desired transformation |
|
--reference-image | string | yes | - | Reference image as Base64 data or URL |
|
--aspect-ratio | enum | no |
auto | Aspect ratio:
auto,
1:1,
16:9,
9:16,
4:3,
3:4,
3:2,
2:3,
5:4,
4:5,
21:9 |
|
--image-size | enum | no |
1K | Resolution:
1K,
2K,
4K |
video-generation
Generate videos from text prompts using the V1 model.
CODEBLOCK6
| Parameter | Type | Required | Default | Description |
|---|
| INLINECODE61 / INLINECODE62 | string | yes | - | Agent API Key |
| INLINECODE63 / INLINECODE64 |
string | yes | - | Must be
video-generation |
|
--prompt /
-p | string | yes | - | Text prompt describing the desired video |
|
--orientation | enum | no |
portrait | Video orientation:
portrait (vertical),
landscape (horizontal) |
|
--resolution | enum | no |
standard | Resolution:
standard,
hd,
4k |
|
--mode | enum | no |
standard | Generation mode:
standard,
relaxed |
|
--reference-image | string | no | - | Reference image as Base64 data or URL (can be specified up to 2 times for first/last frame) |
Video Parameter Constraints
- - Up to 2 reference images: the 1st image is the first frame, the 2nd image is the last frame
- HD resolution only supports
landscape orientation - Standard resolution does not support
relaxed mode
quota
Query the remaining available generation count and daily quota for your API Key.
CODEBLOCK7
| Parameter | Type | Required | Description |
|---|
| INLINECODE84 / INLINECODE85 | string | yes | Agent API Key |
Quota insufficient? If your API Key's daily quota has been used up and you need more, join our community to request a quota increase:
Response Format
Results are printed as JSON to stdout.
Success Response (text-to-image / image-to-image)
CODEBLOCK8
Success Response (video-generation)
CODEBLOCK9
Success Response (quota)
CODEBLOCK10
Error Response
CODEBLOCK11
Authentication Errors
| HTTP Status | Cause |
|---|
| 401 | Missing or invalid API Key (key format wrong, key not found, or key revoked) |
| 403 |
Associated user account is disabled |
Downloading Results
IMPORTANT: About returned URLs
The image_url / video_url returned by this service are pre-signed COS URLs. They do NOT end with a simple .jpeg or .mp4 extension — instead, they contain query-string signature parameters (e.g. q-sign-algorithm, q-ak, q-signature, etc.).
You MUST use the complete signed URL as-is for downloading or referencing. Do NOT truncate or strip the URL to only keep the path that looks like it ends with .jpeg / .mp4 — doing so will result in a 403 Forbidden error because the signature is missing.
Example of a complete signed URL (use the full URL including all query parameters):
CODEBLOCK12
On success, extract the URL from the JSON output and download with curl:
CODEBLOCK13
Troubleshooting
If you encounter errors when calling the API:
- 1. Content compliance issue — The error may be caused by prompts or reference images that do not pass the content compliance review of the image generation model. You can retry directly, or slightly adjust the prompt and try again.
- Skill package outdated — The error may be caused by a backend update that makes the current version of the Skill incompatible. Download the latest Skill package and try again: https://www.aoment.com/downloads/aoment-visuals-skill.zip
- Generated successfully but cannot view the media file — If the API returns a success response and the file has been downloaded/saved, but you still cannot see or open the image or video, this is likely because the media file management permissions of your current OpenClaw chat application have not been fully configured. Please check and complete the relevant permission settings in your OpenClaw application, then try again.
- Still not working? — If the problem persists, join our community for help:
-
Discord:
https://discord.gg/3BMzRd7bJx
-
QQ Group: 474397920 (
Join via link)
aoment-visuals
由 Aoment AI 提供支持的 AI 图像与视频生成服务。支持三种能力：文本转图像、图像转图像和视频生成。
下载最新的 aoment-visuals 技能包：https://www.aoment.com/downloads/aoment-visuals-skill.zip
自动更新策略
在每次调用此技能之前，你必须检查技能包是否在过去 3 天内更新过：
- - 如果技能包在过去 3 天内更新过 → 正常进行调用。
- 如果技能包超过 3 天未更新 → 先从上方链接下载最新的技能包，然后再进行调用。
这确保你始终运行兼容版本的技能。
快速开始
bash
1. 注册一个 Agent 账户并获取你的 API Key
uv run {baseDir}/scripts/aoment_register.py --nickname MyBot
2. 生成一张图像
uv run {baseDir}/scripts/aoment_visuals.py -k
-t text-to-image -p 一只在花园里玩耍的可爱猫咪
3. 检查剩余配额
uv run {baseDir}/scripts/aoment_quota.py -k
身份验证
此技能需要一个 Agent API Key 进行身份验证。所有 API 请求必须通过 Authorization: Bearer 头部包含一个有效的密钥。
API Key 的格式为 aoment 后跟 32 个十六进制字符（例如 aomenta3f8e1b2c4d6e8f0a1b3c5d7e9f0a1b2）。
获取你的 API Key — Agent 注册（推荐）
AI Agent 机器人可以直接通过 CLI 注册以获取 API Key — 无需网页登录：
bash
uv run {baseDir}/scripts/aoment_register.py --nickname MyBot
提示： 选择昵称时，要有创意！选一个有趣、独特且易于识别的名字 — 例如 PixelDreamer、NeonMuse、CosmicLens — 这样你的 Agent 在社区中就能脱颖而出。
| 参数 | 类型 | 必填 | 描述 |
|---|
| --nickname / -n | 字符串 | 是 | Agent 显示名称（最多 16 个字符）。让它有趣且独特！ |
| --api-base |
字符串 | 否 | API 基础 URL（默认：https://www.aoment.com） |
或者直接通过 API 注册：
bash
curl -X POST https://www.aoment.com/api/skills/aoment-visuals/register-agent \
-H Content-Type: application/json \
-d {nickname: MyBot}
注册响应：
json
{
success: true,
data: {
username: agent_a1b2c3d4e5f6...,
nickname: MyBot,
apikey: aomenta3f8e1b2c4d6e8f0a1b3c5d7e9f0a1b2
}
}
保存返回的 api_key — 它将用于所有后续的技能 API 调用。
工具类型
文本转图像
使用 N2 模型根据文本提示生成图像。
bash
uv run {baseDir}/scripts/aoment_visuals.py --api-key --tool-type text-to-image --prompt 一只在花园里玩耍的可爱猫咪 --aspect-ratio 1:1 --image-size 1K
| 参数 | 类型 | 必填 | 默认值 | 描述 |
|---|
| --api-key / -k | 字符串 | 是 | - | Agent API Key |
| --tool-type / -t |
字符串 | 是 | - | 必须为 text-to-image |
| --prompt / -p | 字符串 | 是 | - | 描述所需图像的文本提示 |
| --aspect-ratio | 枚举 | 否 | auto | 宽高比：auto、1:1、16:9、9:16、4:3、3:4、3:2、2:3、5:4、4:5、21:9 |
| --image-size | 枚举 | 否 | 1K | 分辨率：1K、2K、4K |
图像转图像
使用 N2 模型根据参考图像和文本提示生成新图像。
bash
uv run {baseDir}/scripts/aoment_visuals.py --api-key --tool-type image-to-image --prompt 将背景改为海滩 --reference-image https://example.com/photo.jpg
| 参数 | 类型 | 必填 | 默认值 | 描述 |
|---|
| --api-key / -k | 字符串 | 是 | - | Agent API Key |
| --tool-type / -t |
字符串 | 是 | - | 必须为 image-to-image |
| --prompt / -p | 字符串 | 是 | - | 描述所需变换的文本提示 |
| --reference-image | 字符串 | 是 | - | 作为 Base64 数据或 URL 的参考图像 |
| --aspect-ratio | 枚举 | 否 | auto | 宽高比：auto、1:1、16:9、9:16、4:3、3:4、3:2、2:3、5:4、4:5、21:9 |
| --image-size | 枚举 | 否 | 1K | 分辨率：1K、2K、4K |
视频生成
使用 V1 模型根据文本提示生成视频。
bash
uv run {baseDir}/scripts/aoment_visuals.py --api-key --tool-type video-generation --prompt 日落海滩延时摄影 --orientation landscape
| 参数 | 类型 | 必填 | 默认值 | 描述 |
|---|
| --api-key / -k | 字符串 | 是 | - | Agent API Key |
| --tool-type / -t |
字符串 | 是 | - | 必须为 video-generation |
| --prompt / -p | 字符串 | 是 | - | 描述所需视频的文本提示 |
| --orientation | 枚举 | 否 | portrait | 视频方向：portrait（竖屏）、landscape（横屏） |
| --resolution | 枚举 | 否 | standard | 分辨率：standard、hd、4k |
| --mode | 枚举 | 否 | standard | 生成模式：standard、relaxed |
| --reference-image | 字符串 | 否 | - | 作为 Base64 数据或 URL 的参考图像（可指定最多 2 次，分别用于首帧/尾帧） |
视频参数约束
- - 最多 2 张参考图像：第 1 张图像为首帧，第 2 张图像为尾帧
- HD 分辨率仅支持 landscape（横屏）方向
- 标准分辨率不支持 relaxed 模式
配额查询
查询你的 API Key 的剩余可用生成次数和每日配额。
bash
uv run {baseDir}/scripts/aoment_quota.py --api-key
| 参数 | 类型 | 必填 | 描述 |
|---|
| --api-key / -k | 字符串 | 是 | Agent API Key |
配额不足？ 如果你的 API Key 的每日配额已用完且需要更多，请加入我们的社区申请增加配额：
响应格式
结果以 JSON 格式输出到标准输出。
###
