higgsfield-image-auto

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Higgsfield Image Auto-Generate via Playwright

通过Playwright实现Higgsfield图像自动生成

This skill automates the full Higgsfield image generation flow using Playwright browser automation. It navigates to the image generation page, enters a prompt, configures settings, and clicks Generate — hands-free.

本技能使用Playwright浏览器自动化完成Higgsfield图像生成的全流程。它会导航至图像生成页面、输入提示词、配置设置并点击生成——全程无需手动操作。

Prerequisites

前提条件

User must be logged in to higgsfield.ai in the Playwright browser session
Playwright MCP plugin must be enabled
Load each Playwright tool with
```
ToolSearch
```
before first use

用户必须在Playwright浏览器会话中已登录higgsfield.ai
必须启用Playwright MCP插件
首次使用前需通过
```
ToolSearch
```
加载每个Playwright工具

Input Requirements

输入要求

The user provides:

A text prompt for the image (or invoke
```
/ugc-hot-girl
```
first to generate one)

Optional overrides (defaults shown):

Model:
```
Soul 2.0
```
(options: Soul 2.0, Soul Cinema, Nano Banana Pro, Nano Banana 2, Seedream 5.0 lite, GPT Image 1.5, Grok Imagine, FLUX.2, Reve, Z-Image)
Aspect Ratio:
```
3:4
```
(options: 1:1, 3:4, 4:3, 9:16, 16:9, 2:3, 3:2)
Resolution:
```
2k
```
(options: 1k, 2k, 4k)
Image Count:
```
1
```
(options: 1-4)

用户需提供：

图像文本提示词（或先调用
```
/ugc-hot-girl
```
生成提示词）

可选自定义设置（默认值如下）：

模型：
```
Soul 2.0
```
（可选：Soul 2.0、Soul Cinema、Nano Banana Pro、Nano Banana 2、Seedream 5.0 lite、GPT Image 1.5、Grok Imagine、FLUX.2、Reve、Z-Image）
宽高比：
```
3:4
```
（可选：1:1、3:4、4:3、9:16、16:9、2:3、3:2）
分辨率：
```
2k
```
（可选：1k、2k、4k）
图像数量：
```
1
```
（可选：1-4）

Model URL Map

模型URL映射

Each model has its own URL path:

Model	URL
Soul 2.0	`/image/soul-v2`
Soul Cinema	`/image/soul-cinematic`
Nano Banana Pro	`/image/nano-banana-pro`
Nano Banana 2	`/image/nano-banana-2`
Seedream 5.0 lite	`/image/seedream_v5_lite`
GPT Image 1.5	`/image/openai_hazel`
Grok Imagine	`/image/grok_image`
FLUX.2	`/image/flux_2`
Reve	`/image/reve`
Z-Image	`/image/z-image`

Default: Soul 2.0 (

/image/soul-v2

) — best for photorealistic portraits and UGC characters.

每个模型对应独立的URL路径：

模型	URL
Soul 2.0	`/image/soul-v2`
Soul Cinema	`/image/soul-cinematic`
Nano Banana Pro	`/image/nano-banana-pro`
Nano Banana 2	`/image/nano-banana-2`
Seedream 5.0 lite	`/image/seedream_v5_lite`
GPT Image 1.5	`/image/openai_hazel`
Grok Imagine	`/image/grok_image`
FLUX.2	`/image/flux_2`
Reve	`/image/reve`
Z-Image	`/image/z-image`

默认值：Soul 2.0（

/image/soul-v2

）——最适合生成写实肖像和UGC角色。

Automation Flow

自动化流程

Step 1: Navigate to the image generation page

步骤1：导航至图像生成页面

browser_navigate → url: "https://higgsfield.ai/image/soul-v2"

Replace

soul-v2

with the appropriate model path from the table above if the user requests a different model.

Wait for the page to load, then take a snapshot to confirm:

The page title contains the model name
The prompt textbox is visible

browser_navigate → url: "https://higgsfield.ai/image/soul-v2"

若用户请求其他模型，将

soul-v2

替换为上表中对应的模型路径。

等待页面加载完成后，截取快照确认：

页面标题包含模型名称
提示词输入框可见

Step 2: Find and click the prompt textbox

步骤2：找到并点击提示词输入框

Take a snapshot. Look for:

textbox [ref=eXX]

It's inside

group [ref=eXX]

at the bottom of the page. The placeholder text is "Describe the scene you imagine".

The textbox has a Playwright ID:

[id="hf:tour-image-prompt"]

— Playwright may use this selector automatically.

browser_click → ref: <textbox_ref>, element: "Image prompt textbox"

截取快照，查找：

textbox [ref=eXX]

它位于页面底部的

group [ref=eXX]

内，占位文本为“Describe the scene you imagine”。

该输入框的Playwright ID为：

[id="hf:tour-image-prompt"]

——Playwright会自动使用此选择器。

browser_click → ref: <textbox_ref>, element: "Image prompt textbox"

Step 3: Type the prompt

步骤3：输入提示词

browser_type → ref: <textbox_ref>, text: "<the image prompt>"

Important: Use the

fill

method (default), NOT

slowly: true

. The textbox is a standard input, not a Lexical editor.

browser_type → ref: <textbox_ref>, text: "<the image prompt>"

重要提示：使用

fill

方法（默认设置），不要使用

slowly: true

。此输入框为标准输入框，而非Lexical编辑器。

Step 4: Adjust settings (optional)

步骤4：调整设置（可选）

If the user wants non-default settings, click the corresponding buttons:

Aspect Ratio — Find the button showing current ratio (e.g., "3:4"):

browser_click → ref: <ratio_button_ref>, element: "Aspect ratio selector"

Then select from the dropdown options.

Resolution — Find the button showing current resolution (e.g., "2k"):

browser_click → ref: <resolution_button_ref>, element: "Resolution selector"

Image Count — Find the increment/decrement buttons (shows "1/4"):

Click the "Increment" button to increase count (max 4)
Click the "Decrement" button to decrease

Character/Moodboard — The right side panel shows "CHARACTER" with a "General" moodboard. Click "Change" to switch.

若用户需要非默认设置，点击对应按钮：

宽高比——找到显示当前比例的按钮（如“3:4”）：

browser_click → ref: <ratio_button_ref>, element: "Aspect ratio selector"

然后从下拉选项中选择。

分辨率——找到显示当前分辨率的按钮（如“2k”）：

browser_click → ref: <resolution_button_ref>, element: "Resolution selector"

图像数量——找到增减按钮（显示“1/4”）：

点击“Increment”按钮增加数量（最多4张）
点击“Decrement”按钮减少数量

角色/情绪板——右侧面板显示“CHARACTER”及“General”情绪板，点击“Change”切换。

Step 5: Generate

步骤5：生成图像

Take a screenshot to show the user the form state.

ASK THE USER FOR CONFIRMATION before clicking Generate — this uses credits/free generations.

Find and click the Generate button:

browser_click → ref: <generate_button_ref>, element: "Generate button"

The Generate button shows remaining free generations (e.g., "Generate 4915 free gens left").

截取截图展示表单状态。

点击生成前请向用户确认——此操作会消耗点数或免费生成额度。

找到并点击生成按钮：

browser_click → ref: <generate_button_ref>, element: "Generate button"

生成按钮会显示剩余免费生成次数（如“Generate 4915 free gens left”）。

Step 6: Wait for generation

步骤6：等待生成完成

browser_wait_for → time: 15

Image generation typically takes 10-20 seconds on Soul 2.0.

browser_wait_for → time: 15

使用Soul 2.0生成图像通常需要10-20秒。

Step 7: Verify the result

步骤7：验证结果

Take a screenshot. The newly generated image appears as the first item in the History grid at the top of the page.

To view the full image, click on the first grid item. This opens an "Asset showcase" dialog with:

Full-size image preview
Prompt details
Action buttons: Overview, Upscale, Enhancer, Relight, Inpaint, Angles
Bottom actions: Animate, Publish, Open in, Reference, Download

截取截图。新生成的图像会显示在页面顶部历史网格的第一个位置。

点击第一个网格项可查看完整图像，这会打开“Asset showcase”对话框，包含：

全尺寸图像预览
提示词详情
操作按钮：Overview、Upscale、Enhancer、Relight、Inpaint、Angles
底部操作：Animate、Publish、Open in、Reference、Download

Step 8: Report to user

步骤8：向用户反馈

Tell the user the image was generated successfully. If this is part of the UGC pipeline, remind them they can now use

/seedance-auto-generate

to create a video from this image.

告知用户图像已成功生成。若此为UGC流水线的一部分，提醒用户现在可使用

/seedance-auto-generate

将该图像制作成视频。

Key Element Patterns

关键元素定位规则

These patterns help navigate the page. Refs change between sessions — always take a fresh snapshot.

Element	How to find it
Prompt textbox	`textbox` with Playwright ID `hf:tour-image-prompt`
Model selector	`button` inside `group` containing model name (e.g., "Soul 2.0")
Aspect ratio	`button` showing ratio text (e.g., "3:4") with dropdown arrow
Resolution	`button` showing resolution (e.g., "2k") with dropdown arrow
Image count	`button "Decrement/Increment"` with counter showing "X/4"
Color Transfer	`button "Color Transfer New"`
Character panel	`complementary` section on the right with "CHARACTER" label
Generate button	`button "Generate ..."` with free gen count
History grid	`generic` container with multiple `img "image generation"` children
First generated image	First `generic` child inside the History grid container

这些规则可帮助导航页面。Ref值会在不同会话间变化——每次都需截取新快照。

元素	定位方式
提示词输入框	带有Playwright ID `hf:tour-image-prompt` 的 `textbox`
模型选择器	包含模型名称（如“Soul 2.0”）的 `group` 内的 `button`
宽高比	显示比例文本（如“3:4”）并带有下拉箭头的 `button`
分辨率	显示分辨率（如“2k”）并带有下拉箭头的 `button`
图像数量	带有计数器“X/4”的“Decrement/Increment” `button`
颜色迁移	“Color Transfer New” `button`
角色面板	右侧带有“CHARACTER”标签的 `complementary` 区域
生成按钮	带有免费生成次数的“Generate ...” `button`
历史网格	包含多个 `img "image generation"` 子元素的 `generic` 容器
首个生成图像	历史网格容器内的第一个 `generic` 子元素

Error Handling

错误处理

Not logged in: If the page shows a login prompt, ask user to log in (
```
! open https://higgsfield.ai
```
)
Prompt textbox not found: The input bar occasionally doesn't render. Refresh the page and retry.
Model not available: Some models require a subscription. Check for upgrade prompts.
Generation failed: The image will show "Failed" status in the grid. Suggest retrying or simplifying the prompt.

未登录：若页面显示登录提示，请用户登录（
```
! open https://higgsfield.ai
```
）
未找到提示词输入框：输入栏偶尔无法渲染，刷新页面后重试
模型不可用：部分模型需要订阅，检查是否有升级提示
生成失败：图像在网格中会显示“Failed”状态，建议重试或简化提示词

Pipeline Integration

流水线集成

This skill is step 2 of the UGC pipeline:

/ugc-hot-girl
— Generates the character image prompt
/higgsfield-image-auto
← You are here — automates image generation on Higgsfield
/seedance-auto-generate
— Takes the generated image to Seedance 2.0 video page

本技能是UGC流水线的第2步：

/ugc-hot-girl
—— 生成角色图像提示词
/higgsfield-image-auto
← 当前技能 —— 自动化在Higgsfield上生成图像
/seedance-auto-generate
—— 将生成的图像导入Seedance 2.0视频页面

How the image flows to video

图像流转至视频的方式

After generating an image here, it's automatically available in the Seedance 2.0 video creation page:

Navigate to
```
/create/video?model=seedance_2_0
```
Click the upload area → opens media dialog
Click "Image Generations" tab
The most recently generated image appears as the first item
Click it to select (it changes from "Check eligibility" button to a selected state with green checkmark)
Press Escape to close dialog — the image is now loaded into the video form

No file download/upload needed — Higgsfield's internal asset system connects image generations directly to video creation.

在此生成图像后，它会自动同步到Seedance 2.0视频创建页面：

导航至
```
/create/video?model=seedance_2_0
```
点击上传区域 → 打开媒体对话框
点击**“Image Generations”**标签页
最新生成的图像会显示在第一个位置
点击选中（按钮会从“Check eligibility”变为带有绿色对勾的选中状态）
按Escape关闭对话框 —— 图像已加载至视频表单

无需下载/上传文件 —— Higgsfield的内部资产系统将图像生成与视频创建直接关联。