transformation-builder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Transformation Builder Skill

Transformation Builder Skill

Understand how the tool works, write a precise query, order multi-step chains correctly, then call
transformation_builder
.
了解该工具的工作原理,编写精准的查询语句,正确排序多步骤转换链,然后调用
transformation_builder

How this tool actually works (read this first)

工具实际工作原理(请先阅读)

transformation_builder
is not a capability picker. Its only inputs are:
transformation_builder(query, src?, previous_errors?)
  • query
    — a natural-language description of the desired transformation.
  • src
    — optional ImageKit-hosted source URL (defaults to a sample image).
  • previous_errors
    — pass the error text from a prior failed call so the tool can self-correct.
Internally the tool: (1) searches ImageKit docs using your
query
, (2) an LLM turns it into a validated list of transformation steps, (3) the SDK builds the final URL. There is no
capability
argument
— the parameter names below are vocabulary to put into your query, not API fields you set directly. Because step 1 is a doc search over your query text, using the correct ImageKit parameter names and values in the query materially improves the result. Using wrong/invented names sends the search off course.
So your job is: translate the user's vague request into a precise query that references real parameters and values from the reference section below.
transformation_builder
不是功能选择器。它仅接受以下输入:
transformation_builder(query, src?, previous_errors?)
  • query
    — 对所需转换效果的自然语言描述。
  • src
    — 可选的ImageKit托管源URL(默认使用示例图片)。
  • previous_errors
    — 传入之前调用失败的错误文本,以便工具自我纠正。
工具内部流程:(1) 使用你的
query
搜索ImageKit文档,(2) 大语言模型将其转换为经过验证的转换步骤列表,(3) SDK构建最终URL。此工具没有
capability
参数
——下方的参数名称是需要放入查询语句的词汇,而非直接设置的API字段。由于第一步是对查询文本进行文档搜索,在查询中使用正确的ImageKit参数名称和值能显著提升结果质量。使用错误/虚构的名称会导致搜索偏离方向。
因此你的任务是:将用户模糊的需求转换为精准的查询语句,引用下方参考部分中的真实参数和值。

When to use (triggers this skill)

使用场景(触发此技能)

  • Resize, crop, or focus on a region
  • Filters, effects, overlays (image/text/video), watermarks
  • Multi-step transformation chains
  • Background removal, replacement, or generative fill
  • Any AI-powered image editing (change objects/colors/styles, upscale, retouch, drop shadow, variations)
  • 调整大小、裁剪或聚焦特定区域
  • 滤镜、特效、叠加层(图像/文字/视频)、水印
  • 多步骤转换链
  • 背景移除、替换或生成式填充
  • 任何AI驱动的图像编辑(更改对象/颜色/样式、放大、润色、投影、变体)

Calling
transformation_builder

调用
transformation_builder

  • query
    : the precise, rewritten description (see Query Crafting). Never pass the user's vague words through unchanged.
  • src
    : the ImageKit delivery URL to transform, if the user gave one. Must be ImageKit-hosted.
  • Frame a multi-step request as one query describing the steps in order:
    • User: "1) Resize to 800x600 2) Crop to the face"
    • Query: "Resize to width 800 and height 600, then crop with focus on the face"
  • query
    :经过精准改写的描述(参见查询语句编写)。切勿直接传递用户模糊的原始表述
  • src
    :用户提供的待转换ImageKit交付URL(必须是ImageKit托管的)。
  • 将多步骤请求整理为一个查询语句,按顺序描述步骤:
    • 用户:"1) 调整为800x600 2) 裁剪至人脸区域"
    • 查询语句:"调整宽度为800、高度为600,然后以人脸为焦点进行裁剪"

Query Crafting

查询语句编写

Rule: rewrite the vague request into a description that names real parameters and values. Use exact parameter names/values when you know them; fall back to plain English only when unsure.
User saysWeak queryGood query
"Make the red balls green""make red balls green""Apply an AI edit (
ai_edit
) with prompt: change the red balls to green"
"Clean it up and put it on white""clean up, white background""Apply
ai_retouch
, then
ai_remove_background
with white background color"
"Make it look like a painting""painting style""Apply
ai_edit
with prompt: oil-painting style with visible brush strokes"
"Crop around the face""crop face""Resize with
focus
=
face
to crop around the detected face"
"Text 'Hello' at the bottom""add hello text""Add a text overlay with text 'Hello', positioned at the bottom (
focus
=
bottom
)"
"Fit a mobile banner""mobile banner""Resize to
width
=640 with
aspect_ratio
=2-1"
"300px wide with a red border""resize and border""Resize to
width
=300, then add a
border
of width 5 and color red"
"Higher resolution, it's blurry""fix quality""Apply
ai_upscale
, then
ai_retouch
"
"Remove bg and add a shadow""remove bg shadow""Apply
ai_remove_background
, then
ai_drop_shadow
"
"Make it wider without stretching""make wider""Extend the canvas horizontally using a padded crop (
crop_mode
=
pad_extract
) with
background
=
genfill
so AI fills the new area"
规则:将模糊的需求改写为提及真实参数和值的描述。已知参数名称/值时使用准确表述;不确定时再退而使用直白英语。
用户表述欠佳的查询语句优质的查询语句
"把红球改成绿色""make red balls green""应用AI编辑(
ai_edit
),提示词:将红球改为绿色"
"清理图片并放在白色背景上""clean up, white background""应用
ai_retouch
,然后使用
ai_remove_background
并设置背景色为白色"
"让它看起来像油画""painting style""应用
ai_edit
,提示词:带有明显笔触的油画风格"
"裁剪人脸区域""crop face""使用
focus
=
face
进行调整大小,以裁剪出检测到的人脸区域"
"在底部添加文字'Hello'""add hello text""添加文字叠加层,内容为'Hello',位置设置为底部(
focus
=
bottom
)"
Fit a mobile banner""mobile banner""调整宽度为
width
=640,
aspect_ratio
=2-1"
"300px宽并添加红色边框""resize and border""调整宽度为
width
=300,然后添加宽度为5、颜色为红色的
border
"
"分辨率更高一点,图片模糊""fix quality""应用
ai_upscale
,然后应用
ai_retouch
"
"移除背景并添加阴影""remove bg shadow""应用
ai_remove_background
,然后应用
ai_drop_shadow
"
"加宽图片但不拉伸""make wider""使用填充裁剪(
crop_mode
=
pad_extract
)水平扩展画布,设置
background
=
genfill
让AI填充新增区域"

Intent → real parameter/vocabulary

需求 → 真实参数/词汇

Use this to translate intent into the correct terms to put in the query. These are the actual parameter names the tool validates against.
User intentUse this vocabularyNotes
Modify specific objects/regions ("enlarge the cat", "add sunglasses", "make it a painting")
ai_edit
(prompt-based)
AI content edit driven by a text prompt
Replace the whole background scene ("put them on a beach")
ai_change_background
(prompt-based)
Keeps the subject, generates a new scene. Not for plain removal or color changes
Remove background → transparent
ai_remove_background
ImageKit-native. For the external remove.bg engine use
ai_remove_background_external
Extend/outpaint the canvas ("add more sky", "make it panoramic")padded crop +
background
=
genfill
Generative fill lives in the background param, not a standalone AI field. Takes no prompt
Increase resolution / fix low-res
ai_upscale
Boolean; no params
Clean up / remove blemishes
ai_retouch
Boolean; no params
Realistic shadow under a cut-out subject
ai_drop_shadow
Transparent images only. Optional
azimuth
,
elevation
,
strength
Different version / remix
ai_variation
Boolean; preserves structure
Resize / aspect ratio / crop
width
,
height
,
aspect_ratio
,
crop
,
crop_mode
See Resize & Crop table
Smart crop to face/object
focus
(
auto
,
face
, or an object name) + optional
zoom
Object names are COCO classes (
person
,
car
,
dog
, …)
Swap one color across all pixels ("all red → blue")
color_replace
Global pixel color swap with
tolerance
Filters/adjustments (B&W, blur, sharpen, rotate, border, round corners)
grayscale
,
blur
,
sharpen
,
rotation
,
border
,
radius
, …
See Effects table
Overlay a logo/watermark imagetext/image overlaySingle
overlay
concept, typed (see Overlays)
Write text on the imagetext overlay with
text
See Overlays
There is no "generate an image from scratch" step in this tool — it always transforms an existing
src
. To generate images from scratch, use text-to-image generation in the ImageKit DAM (Digital Asset Manager), which is a separate feature from
transformation_builder
.
使用下表将用户需求转换为查询语句中应使用的正确术语。这些是工具会验证的实际参数名称。
用户需求使用以下词汇说明
修改特定对象/区域("放大猫"、"添加太阳镜"、"改成油画风格")
ai_edit
(基于提示词)
由文本提示词驱动的AI内容编辑
替换整个背景场景("把他们放在海滩上")
ai_change_background
(基于提示词)
保留主体,生成新场景。不适用于单纯移除背景或更改背景颜色
移除背景 → 透明
ai_remove_background
ImageKit原生功能。如需使用外部remove.bg引擎,请使用
ai_remove_background_external
扩展画布("添加更多天空"、"改为全景图")填充裁剪 +
background
=
genfill
生成式填充属于background参数,而非独立的AI字段。无需提示词
提高分辨率/修复低分辨率图片
ai_upscale
布尔值;无额外参数
清理/去除瑕疵
ai_retouch
布尔值;无额外参数
为抠图主体添加逼真阴影
ai_drop_shadow
仅适用于透明图片。可选参数
azimuth
elevation
strength
生成不同版本/ remix
ai_variation
布尔值;保留原图结构
调整大小/宽高比/裁剪
width
,
height
,
aspect_ratio
,
crop
,
crop_mode
请查看调整大小与裁剪表格
智能裁剪至人脸/物体
focus
auto
face
或物体名称) + 可选
zoom
物体名称为COCO类别(
person
car
dog
等)
替换所有像素中的某一种颜色("所有红色→蓝色")
color_replace
全局像素颜色替换,支持
tolerance
参数
滤镜/调整(黑白、模糊、锐化、旋转、边框、圆角)
grayscale
,
blur
,
sharpen
,
rotation
,
border
,
radius
请查看特效表格
叠加logo/水印图片text/image overlay统一使用
overlay
概念,区分类型(参见叠加层部分)
在图片上添加文字text overlay +
text
请查看叠加层部分
此工具没有"从头生成图片"的功能——它始终转换现有
src
图片。如需从头生成图片,请使用ImageKit DAM(数字资产管理器)中的文本生成图片功能,这是独立于
transformation_builder
的功能。

Key distinction:
ai_edit
vs
color_replace
vs
ai_change_background

关键区别:
ai_edit
vs
color_replace
vs
ai_change_background

  1. Changing specific objects/regions ("make the balls bigger", "turn the car red") →
    ai_edit
  2. Swapping one color globally across all pixels ("replace all red with blue") →
    color_replace
  3. Replacing the entire background scene ("put them on a beach") →
    ai_change_background
  1. 修改特定对象/区域("放大球"、"把车改成红色")→
    ai_edit
  2. 全局替换某一种颜色("将所有红色替换为蓝色")→
    color_replace
  3. 替换整个背景场景("把他们放在海滩上")→
    ai_change_background

Ordering multi-step chains

多步骤转换链排序

When a request spans multiple operations, chain them in one query in this order:
  1. Upscale / retouch (quality first)
  2. AI content edits (
    ai_edit
    )
  3. Background removal / replacement (
    ai_remove_background
    ,
    ai_change_background
    )
  4. Resize / crop (final dimensions)
  5. Effects / overlays (finishing touches)
Critical: background removal goes AFTER upscale/retouch, never before. Correct:
ai_upscale → ai_remove_background
. Wrong:
ai_remove_background → ai_upscale
.
Example — "clean up this photo, remove the background, make it 500x500": → Query: "Apply
ai_retouch
, then
ai_remove_background
, then resize to
width
=500 and
height
=500".
当请求包含多个操作时,按以下顺序将它们整合到一个查询语句中
  1. 放大/润色(优先保证质量)
  2. AI内容编辑
    ai_edit
  3. 背景移除/替换
    ai_remove_background
    ,
    ai_change_background
  4. 调整大小/裁剪(最终尺寸)
  5. 特效/叠加层(收尾处理)
重要提示:背景移除操作应在放大/润色之后进行,切勿提前。 正确顺序:
ai_upscale → ai_remove_background
。错误顺序:
ai_remove_background → ai_upscale
示例——"清理这张照片,移除背景,调整为500x500": → 查询语句:"应用
ai_retouch
,然后应用
ai_remove_background
,最后调整宽度为
width
=500、高度为
height
=500"。

Background removal: clarify intent

背景移除:明确需求

  • If the user says "remove background" ambiguously, ask whether they want:
    1. Real-time URL
      ai_remove_background
      in a delivery URL (nothing stored).
    2. Remove and save — apply the background-removal extension and upload the result as a new file version (a media-library operation, not this tool).
  • Only use
    ai_change_background
    when they want a new background scene. For a plain transparent cut-out or a solid color, use
    ai_remove_background
    (optionally followed by
    background
    =a color).
  • 如果用户模糊地说"移除背景",请询问他们需要:
    1. 实时URL — 在交付URL中使用
      ai_remove_background
      (无存储操作)。
    2. 移除并保存 — 应用背景移除扩展并将结果作为新版本文件上传(这是媒体库操作,不属于此工具)。
  • 仅当用户需要新的背景场景时使用
    ai_change_background
    。如需生成透明抠图或纯色背景,请使用
    ai_remove_background
    (可选择性添加
    background
    =颜色参数)。

Handling failures

处理调用失败

  1. 400 / Bad Request or validation error: refine the query and retry, passing the error text as
    previous_errors
    . Invoke the
    search-docs
    skill and call
    search_docs
    to confirm supported parameters/limits.
  2. 3+ failures: use
    search-docs
    to find supported methods and constraints before retrying.
  3. Unsupported: confirm via docs and offer the closest supported alternative.
  1. 400 / 请求错误或验证错误:优化查询语句并重试,将错误文本作为
    previous_errors
    传入。调用
    search-docs
    技能,使用
    search_docs
    确认支持的参数/限制。
  2. 失败3次及以上:在重试前使用
    search-docs
    查找支持的方法和约束条件。
  3. 不支持的需求:通过文档确认后,提供最接近的支持方案。

Gotchas

注意事项

  • Source URL must be ImageKit-hosted.
  • Background removal order matters (upscale/retouch first).
  • Generative fill =
    background
    =
    genfill
    on a padded/enlarged canvas; it takes no prompt.
    ai_change_background
    is the prompt-driven one.
  • ai_drop_shadow
    needs a transparent subject (run
    ai_remove_background
    first).
  • Negative offsets/rotation are written with an
    N
    prefix in the final URL (the tool handles this) — just describe the value normally.

  • 源URL必须是ImageKit托管的。
  • 背景移除的顺序至关重要(先放大/润色)。
  • 生成式填充 = 在扩展/填充的画布上设置
    background
    =
    genfill
    ;无需提示词。
    ai_change_background
    是基于提示词的背景替换功能。
  • ai_drop_shadow
    需要透明主体(需先运行
    ai_remove_background
    )。
  • 最终URL中负偏移/旋转值带有
    N
    前缀(工具会自动处理)——只需正常描述数值即可。

Parameter reference

参数参考

These are the real names/values the tool validates. Put them into your query.
这些是工具会验证的真实名称/值。请将它们放入查询语句中。

Resize & crop

调整大小与裁剪

ParameterWhat it does
width
Output width. Integer px, decimal 0–1 (fraction of original), or an arithmetic expression.
height
Output height. Same formats as
width
.
aspect_ratio
Aspect ratio (e.g.
16-9
). Use with
width
or
height
; ignored if both are set.
crop
Resize strategy:
force
,
at_max
,
at_max_enlarge
,
at_least
,
maintain_ratio
,
maintain_ratio_no_enlarge
.
crop_mode
Pad/extract behavior:
pad_resize
,
extract
,
pad_extract
,
pad_resize_no_enlarge
,
pad_extract_no_shrink
.
focus
Focal point:
auto
,
face
,
custom
, a directional position (
center
,
top
,
left
,
bottom_right
, …), or an object name (COCO class such as
person
,
car
,
dog
).
zoom
Zoom factor around the focused area (with face/object focus).
x
,
y
,
x_center
,
y_center
Region coordinates for
extract
crops (top-left vs center-based).
dpr
Device pixel ratio (number or
auto
) for high-density displays.
background
Fill for padded areas — see Background modes.
参数功能
width
输出宽度。支持整数像素、0–1的小数(相对于原图的比例)或算术表达式。
height
输出高度。格式与
width
相同。
aspect_ratio
宽高比(例如
16-9
)。需与
width
height
配合使用;若两者都设置则此参数会被忽略。
crop
调整策略:
force
,
at_max
,
at_max_enlarge
,
at_least
,
maintain_ratio
,
maintain_ratio_no_enlarge
crop_mode
填充/提取行为:
pad_resize
,
extract
,
pad_extract
,
pad_resize_no_enlarge
,
pad_extract_no_shrink
focus
焦点:
auto
,
face
,
custom
, 方向位置(
center
,
top
,
left
,
bottom_right
等),或物体名称(COCO类别如
person
,
car
,
dog
)。
zoom
焦点区域的缩放系数(适用于人脸/物体聚焦)。
x
,
y
,
x_center
,
y_center
extract
裁剪的区域坐标(基于左上角或中心)。
dpr
设备像素比(数字或
auto
),适用于高密度显示屏。
background
填充区域的背景模式——请查看背景模式部分。

Background modes (
background
)

背景模式(
background

ValueMeaning
a colorHex (
FFFFFF
) or CSS name (
white
,
red
, …).
blurred
Blurred version of the image (optionally
blurred_<intensity>_<brightness>
).
dominant
The image's dominant color.
genfill
AI generative fill of the padded area (outpainting). No prompt.
gradient
Gradient from dominant colors (
gradient_dominant
, optional palette size 2 or 4).
含义
颜色值十六进制(
FFFFFF
)或CSS颜色名称(
white
,
red
等)。
blurred
图片的模糊版本(可选格式
blurred_<intensity>_<brightness>
)。
dominant
图片的主色调。
genfill
AI生成式填充填充区域(向外扩展绘画)。无需提示词。
gradient
基于主色调的渐变(
gradient_dominant
,可选调色板大小2或4)。

AI transforms

AI转换

ParameterWhat it does
ai_remove_background
ImageKit-native background removal → transparent.
ai_remove_background_external
Background removal via external provider (remove.bg).
ai_edit
Prompt-based AI edit of image content.
ai_change_background
Prompt-based replacement of the background scene (subject preserved).
ai_drop_shadow
AI drop shadow (transparent images only). Optional
azimuth
(0–360),
elevation
(0–90),
strength
(0–100).
ai_upscale
AI super-resolution upscaling. No params.
ai_retouch
AI quality enhancement / blemish removal. No params.
ai_variation
Generate a structural variation of the image. No params.
参数功能
ai_remove_background
ImageKit原生背景移除 → 透明。
ai_remove_background_external
通过外部服务商(remove.bg)移除背景。
ai_edit
基于提示词的AI图像内容编辑。
ai_change_background
基于提示词的背景场景替换(保留主体)。
ai_drop_shadow
AI投影(仅适用于透明图片)。可选参数
azimuth
(0–360)、
elevation
(0–90)、
strength
(0–100)。
ai_upscale
AI超分辨率放大。无额外参数。
ai_retouch
AI质量增强/瑕疵去除。无额外参数。
ai_variation
生成图片的结构变体。无额外参数。

Effects & enhancement

特效与增强

ParameterWhat it does
blur
Gaussian blur, 0–100.
sharpen
Sharpen, 0–100.
unsharp_mask
Advanced sharpening (
radius
,
sigma
,
amount
,
threshold
).
grayscale
Convert to grayscale.
contrast_stretch
Auto-enhance contrast.
shadow
Drop shadow under non-transparent pixels (needs transparency). Optional
blur
,
saturation
,
x_offset
,
y_offset
.
gradient
Linear gradient overlay (
linear_direction
,
from_color
,
to_color
,
stop_point
).
color_replace
Replace a color and similar shades:
to_color
,
tolerance
(0–100), optional
from_color
.
colorize
Tint the image:
color
,
intensity
(0–100).
border
Border of
border_width
and
color
.
trim
Trim solid edges around the subject.
rotation
Rotate by degrees (or
auto
from EXIF). Negative = counter-clockwise.
flip
h
,
v
,
h_v
, or
v_h
.
radius
Round corners (integer,
max
for a circle, or per-corner
20_40_80_160
).
opacity
Layer opacity, 0–100.
distort
Perspective warp (4 coordinate pairs) or arc distortion (degrees).
参数功能
blur
高斯模糊,取值0–100。
sharpen
锐化,取值0–100。
unsharp_mask
高级锐化(
radius
,
sigma
,
amount
,
threshold
)。
grayscale
转换为灰度图。
contrast_stretch
自动增强对比度。
shadow
为非透明像素添加投影(需要透明区域)。可选参数
blur
,
saturation
,
x_offset
,
y_offset
gradient
线性渐变叠加层(
linear_direction
,
from_color
,
to_color
,
stop_point
)。
color_replace
替换颜色及相似色调:
to_color
,
tolerance
(0–100),可选
from_color
colorize
为图片着色:
color
,
intensity
(0–100)。
border
设置
border_width
color
的边框。
trim
裁剪主体周围的纯色边缘。
rotation
旋转角度(或从EXIF自动获取
auto
)。负值表示逆时针旋转。
flip
h
,
v
,
h_v
, 或
v_h
radius
圆角(整数,
max
表示圆形,或按角设置
20_40_80_160
)。
opacity
图层透明度,取值0–100。
distort
透视变形(4组坐标)或弧形变形(角度)。

Overlays (
overlay
)

叠加层(
overlay

One
overlay
concept with a typed shape. Each overlay supports
position
(
x
,
y
,
x_center
,
y_center
,
focus
,
anchor_point
),
timing
for video (
start
,
end
,
duration
),
layer_mode
(
multiply
,
cutter
,
cutout
,
displace
), and a nested
transformation
list.
Overlay typeKey fields
Text
text
, plus styling:
font_size
,
font_family
,
font_color
,
inner_alignment
,
padding
,
alpha
(1–9),
typography
,
line_height
,
radius
,
rotation
,
flip
,
background
.
Image
input
(media-library path of the overlay image); nested transformations allowed.
Video
input
(video path); nested transformations + timing.
Subtitle
input
(subtitle file); styling:
font_size
,
font_family
,
color
,
typography
,
font_outline
,
font_shadow
,
background
.
Solid color
color
, plus
width
,
height
,
radius
,
alpha
,
background
,
gradient
.
统一使用
overlay
概念,区分不同类型。每个叠加层支持
position
x
,
y
,
x_center
,
y_center
,
focus
,
anchor_point
)、视频
timing
start
,
end
,
duration
)、
layer_mode
multiply
,
cutter
,
cutout
,
displace
),以及嵌套的
transformation
列表。
叠加层类型关键字段
文本
text
,以及样式参数:
font_size
,
font_family
,
font_color
,
inner_alignment
,
padding
,
alpha
(1–9),
typography
,
line_height
,
radius
,
rotation
,
flip
,
background
图像
input
(叠加图片的媒体库路径);支持嵌套转换。
视频
input
(视频路径);支持嵌套转换 + 时间参数。
字幕
input
(字幕文件);样式参数:
font_size
,
font_family
,
color
,
typography
,
font_outline
,
font_shadow
,
background
纯色
color
,以及
width
,
height
,
radius
,
alpha
,
background
,
gradient

Video transforms

视频转换

ParameterWhat it does
start_offset
,
end_offset
,
duration
Trim the clip (seconds or arithmetic expressions).
audio_codec
aac
,
opus
, or
none
(to mute/strip).
video_codec
h264
,
vp9
,
av1
, or
none
.
streaming_resolutions
Adaptive-bitrate ladder, e.g.
[360, 720, 1080]
.
rotation
,
radius
,
border
,
flip
Same as image effects, applied to the video frame.
参数功能
start_offset
,
end_offset
,
duration
裁剪视频片段(秒或算术表达式)。
audio_codec
aac
,
opus
, 或
none
(静音/移除音频)。
video_codec
h264
,
vp9
,
av1
, 或
none
streaming_resolutions
自适应比特率阶梯,例如
[360, 720, 1080]
rotation
,
radius
,
border
,
flip
与图像特效相同,应用于视频帧。

Output & delivery

输出与交付

ParameterWhat it does
format
auto
,
webp
,
avif
,
jpg
,
png
,
gif
,
mp4
,
webm
,
orig
, …
quality
0–100.
progressive
Progressive JPEG.
lossless
Lossless WebP/PNG.
named
Apply a saved named transformation.
default_image
Fallback image if the source is missing.
参数功能
format
auto
,
webp
,
avif
,
jpg
,
png
,
gif
,
mp4
,
webm
,
orig
quality
0–100。
progressive
渐进式JPEG。
lossless
无损WebP/PNG。
named
应用已保存的命名转换。
default_image
源图片缺失时的 fallback 图片。

Conditionals

条件转换

Transformations can be conditional on image properties (e.g. width/height/aspect ratio) — describe the condition in plain language ("if width > 1000, then …") and the tool builds the
if
/
if-else
/
if-end
chain.
转换操作可基于图片属性(如宽度/高度/宽高比)设置条件——用直白语言描述条件("如果宽度>1000,则……"),工具会构建
if
/
if-else
/
if-end
链。