videoagent-image-studio

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

🎨 VideoAgent Image Studio

🎨 VideoAgent 图像工作室

Use when: User asks to generate, draw, create, or make any kind of image, photo, illustration, icon, logo, or artwork.

Generate images with 8 state-of-the-art AI models. This skill automatically picks the best model for the job and handles all the complexity — including Midjourney's async polling — so you can focus on the conversation.

适用场景： 用户要求生成、绘制、创建或制作任何类型的图像、照片、插画、图标、logo或艺术作品。

借助8款最先进的AI模型生成图像。这个技能会自动为任务选择最佳模型并处理所有复杂流程——包括Midjourney的异步轮询——让你可以专注于对话本身。

Quick Reference

快速参考

User Intent	Model	Speed
Artistic, cinematic, painterly	`midjourney`	~15s
Photorealistic, portrait, product	`flux-pro`	~8s
General purpose, balanced	`flux-dev`	~10s
Quick draft, fast iteration	`flux-schnell`	~2s
Image with text, logo, poster	`ideogram`	~10s
Vector art, icon, flat design	`recraft`	~8s
Anime, stylized illustration	`sdxl`	~5s
Gemini-powered, consistent style	`nano-banana`	~12s

用户意图	模型	速度
艺术风、电影感、绘画风	`midjourney`	~15s
照片写实、人像、产品	`flux-pro`	~8s
通用场景、均衡表现	`flux-dev`	~10s
快速草稿、快速迭代	`flux-schnell`	~2s
带文字的图像、logo、海报	`ideogram`	~10s
矢量艺术、图标、扁平化设计	`recraft`	~8s
动漫、风格化插画	`sdxl`	~5s
Gemini驱动、风格统一	`nano-banana`	~12s

How to Generate an Image

如何生成图像

Step 1 — Enhance the prompt

步骤1 — 优化提示词

Before calling the script, expand the user's prompt with style, lighting, and quality descriptors appropriate for the chosen model.

Midjourney: Add

cinematic lighting

ultra detailed

--v 7

--style raw

Flux: Add

masterpiece

highly detailed

sharp focus

professional photography

Ideogram: Be explicit about text content, font style, and layout

Recraft: Specify

vector illustration

flat design

icon style

在调用脚本前，根据所选模型的适配要求，补充风格、光照、画质描述来丰富用户的提示词。

Midjourney: 添加

cinematic lighting

、

ultra detailed

、

--v 7

、

--style raw

Flux: 添加

masterpiece

、

highly detailed

、

sharp focus

、

professional photography

Ideogram: 明确说明文字内容、字体风格和排版

Recraft: 指定

vector illustration

、

flat design

、

icon style

Step 2 — Run the script

步骤2 — 运行脚本

bash

node {baseDir}/tools/generate.js \
  --model <model_id> \
  --prompt "<enhanced prompt>" \
  --aspect-ratio <ratio>

All parameters:

Parameter	Default	Description
`--model`	`flux-dev`	Model ID from the table above
`--prompt`	(required)	The image generation prompt
`--aspect-ratio`	`1:1`	`1:1` , `16:9` , `9:16` , `4:3` , `3:4` , `3:2` , `21:9`
`--num-images`	`1`	Number of images (1–4; Midjourney always returns 4)
`--negative-prompt`	—	Things to avoid (not supported by Midjourney)
`--seed`	—	Seed for reproducibility

bash

node {baseDir}/tools/generate.js \\
  --model <model_id> \\
  --prompt "<enhanced prompt>" \\
  --aspect-ratio <ratio>

所有参数：

参数	默认值	描述
`--model`	`flux-dev`	上表中的模型ID
`--prompt`	(必填)	图像生成提示词
`--aspect-ratio`	`1:1`	可选值： `1:1` 、 `16:9` 、 `9:16` 、 `4:3` 、 `3:4` 、 `3:2` 、 `21:9`
`--num-images`	`1`	生成图像数量（1-4；Midjourney固定返回4张）
`--negative-prompt`	—	要排除的内容（Midjourney不支持该参数）
`--seed`	—	用于复现结果的随机种子

Step 3 — Return the result

步骤3 — 返回结果

The script always waits and returns the final image URL(s). No polling required.

json

{
  "success": true,
  "model": "flux-pro",
  "imageUrl": "https://...",
  "images": ["https://..."]
}

Send the

imageUrl

to the user.

脚本会一直等待并返回最终的图片URL，无需自行轮询。

json

{
  "success": true,
  "model": "flux-pro",
  "imageUrl": "https://...",
  "images": ["https://..."]
}

将

imageUrl

发送给用户即可。

Midjourney Actions

Midjourney 操作

After generating a 4-image grid with Midjourney, offer the user these options:

bash

undefined

用Midjourney生成4张图片的网格后，向用户提供以下选项：

bash

undefined

Upscale image #2 (subtle, preserves details)

放大第2张图片（风格柔和，保留细节）

node {baseDir}/tools/generate.js
--model midjourney
--action upscale
--index 2
--job-id <job_id>

node {baseDir}/tools/generate.js \ --model midjourney \ --action upscale \ --index 2 \ --job-id <job_id>

Create a strong variation of image #3

为第3张图片生成强变体

node {baseDir}/tools/generate.js
--model midjourney
--action variation
--index 3
--job-id <job_id>
--variation-type 1

node {baseDir}/tools/generate.js \ --model midjourney \ --action variation \ --index 3 \ --job-id <job_id> \ --variation-type 1

Regenerate with same prompt

使用相同提示词重新生成

node {baseDir}/tools/generate.js
--model midjourney
--action reroll
--job-id <job_id>


**Upscale types:** `0` = Subtle (default, best for photos), `1` = Creative (best for illustrations)

**Variation types:** `0` = Subtle (default), `1` = Strong (dramatic changes)

---

node {baseDir}/tools/generate.js \ --model midjourney \ --action reroll \ --job-id <job_id>


**放大类型：** `0` = 柔和（默认，最适合照片）、`1` = 创意（最适合插画）

**变体类型：** `0` = 柔和（默认）、`1` = 强变体（变化幅度大）

---

Example Conversations

对话示例

User: "Draw a snow leopard on a snowy mountain with cinematic lighting"

bash

undefined

用户： "Draw a snow leopard on a snowy mountain with cinematic lighting"

bash

undefined

Choose midjourney for artistic quality

选择midjourney获得更好的艺术效果

node {baseDir}/tools/generate.js
--model midjourney
--prompt "a majestic snow leopard on a snowy mountain peak, cinematic lighting, dramatic atmosphere, ultra detailed --ar 16:9 --v 7"
--aspect-ratio 16:9


> 🎨 Done! Which one to upscale? (U1-U4) Or create a variant? (V1-V4)

---

**User:** "Use Flux to generate a perfume product poster, white background"

```bash

node {baseDir}/tools/generate.js \ --model midjourney \ --prompt "a majestic snow leopard on a snowy mountain peak, cinematic lighting, dramatic atmosphere, ultra detailed --ar 16:9 --v 7" \ --aspect-ratio 16:9


> 🎨 生成完成！要放大哪一张？（U1-U4）或者生成变体？（V1-V4）

---

**用户：** "Use Flux to generate a perfume product poster, white background"

```bash

Choose flux-pro for photorealistic product shots

选择flux-pro获得写实的产品拍摄效果

node {baseDir}/tools/generate.js
--model flux-pro
--prompt "a luxury perfume bottle on a clean white background, professional product photography, soft shadows, 8k, highly detailed"
--aspect-ratio 3:4


---

**User:** "Show me a quick draft"

```bash

node {baseDir}/tools/generate.js \ --model flux-pro \ --prompt "a luxury perfume bottle on a clean white background, professional product photography, soft shadows, 8k, highly detailed" \ --aspect-ratio 3:4


---

**用户：** "Show me a quick draft"

```bash

flux-schnell for instant previews

使用flux-schnell生成即时预览

node {baseDir}/tools/generate.js
--model flux-schnell
--prompt "..."
--aspect-ratio 1:1


---

**User:** "Make me an App icon, flat style, blue theme"

```bash

node {baseDir}/tools/generate.js \ --model flux-schnell \ --prompt "..." \ --aspect-ratio 1:1


---

**用户：** "Make me an App icon, flat style, blue theme"

```bash

recraft for vector/icon style

使用recraft生成矢量/图标风格内容

node {baseDir}/tools/generate.js
--model recraft
--prompt "a minimal flat design app icon, blue color scheme, simple geometric shapes, vector style, white background"

---

node {baseDir}/tools/generate.js \ --model recraft \ --prompt "a minimal flat design app icon, blue color scheme, simple geometric shapes, vector style, white background"

---

Setup

配置

Zero API keys needed! All requests go through a hosted proxy that handles authentication server-side.

The skill works out of the box — just install and use.

无需API密钥！ 所有请求都通过托管的代理发送，由服务端处理身份验证。

这个技能开箱即用——安装即可使用。

Advanced: Custom proxy or token

进阶：自定义代理或令牌

If you want to use your own proxy or a persistent token, set these environment variables:

json

{
  "skills": {
    "entries": {
      "videoagent-image-studio": {
        "enabled": true,
        "env": {
          "IMAGE_STUDIO_PROXY_URL": "https://your-proxy.vercel.app",
          "IMAGE_STUDIO_TOKEN": "your_token_here"
        }
      }
    }
  }
}

Variable	Required	Description
`IMAGE_STUDIO_PROXY_URL`	No	Custom proxy base URL (default: `https://image-gen-proxy.vercel.app` )
`IMAGE_STUDIO_TOKEN`	No	Persistent token (auto-obtained if not set, 100 free uses per token)

To deploy your own proxy, see the videoagent-audio-studio proxy as a reference implementation. You'll need

FAL_KEY

and

LEGNEXT_KEY

as Vercel environment variables.

如果你想要使用自己的代理或持久化令牌，请设置以下环境变量：

json

{
  "skills": {
    "entries": {
      "videoagent-image-studio": {
        "enabled": true,
        "env": {
          "IMAGE_STUDIO_PROXY_URL": "https://your-proxy.vercel.app",
          "IMAGE_STUDIO_TOKEN": "your_token_here"
        }
      }
    }
  }
}

变量	是否必填	描述
`IMAGE_STUDIO_PROXY_URL`	否	自定义代理基础URL（默认： `https://image-gen-proxy.vercel.app` ）
`IMAGE_STUDIO_TOKEN`	否	持久化令牌（未设置时会自动获取，每个令牌有100次免费使用额度）

要部署自己的代理，可以参考videoagent-audio-studio 代理的实现示例，你需要将

FAL_KEY

和

LEGNEXT_KEY

设置为Vercel的环境变量。

Changelog

更新日志

v2.0.0

Simplified async: The script now blocks until Midjourney completes. No more
```
--async
```
/
```
--poll
```
flags needed in SKILL.md instructions.
Unified output format: All models return the same
```
{ success, imageUrl, images }
```
shape.
Reference images for Nano Banana: Pass
```
--reference-images "url1,url2"
```
for character/style consistency across generations.

简化异步流程： 脚本现在会阻塞直到Midjourney任务完成，SKILL.md说明中不再需要
```
--async
```
/
```
--poll
```
参数。
统一输出格式： 所有模型都返回相同的
```
{ success, imageUrl, images }
```
结构。
Nano Banana支持参考图像： 传入
```
--reference-images "url1,url2"
```
即可在多次生成中保持角色/风格一致性。

v1.3.0

Added non-blocking async mode for Midjourney (
```
--async
```
+
```
--poll
```
).

新增Midjourney非阻塞异步模式（
```
--async
```
+
```
--poll
```
）。

v1.2.0

Midjourney turbo mode enabled by default (~10-20s).

默认开启Midjourney极速模式（~10-20s）。

v1.1.0

Switched Midjourney provider from TTAPI to Legnext.ai for better stability.

Midjourney服务商从TTAPI切换为Legnext.ai，稳定性更高。

v1.0.0

Initial release with Midjourney, Flux, SDXL, Nano Banana, Ideogram, Recraft.

首次发布，支持Midjourney、Flux、SDXL、Nano Banana、Ideogram、Recraft。",