npx skills add https://github.com/eachlabs/skills --skill object-removal使用 each::sense 从照片中移除不需要的元素。此技能智能地移除物体、人物、文字、水印和瑕疵,同时用上下文合适的内容无缝填充被移除的区域。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person standing on the left side of this photo",
"image_urls": ["https://example.com/beach-photo.jpg"],
"mode": "max"
}'
从合影或风景照中移除不需要的人物。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person in the red shirt from this beach photo. Fill the area naturally with the ocean and sand background.",
"image_urls": ["https://example.com/beach-group.jpg"],
"mode": "max"
}'
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
通过移除分散注意力的物体来清理照片。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the trash can and bench from the right side of this park landscape photo. Make it look like a clean natural scene.",
"image_urls": ["https://example.com/park-landscape.jpg"],
"mode": "max"
}'
清理带有不需要文字叠加或水印的图像。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the watermark from the bottom right corner of this image. Restore the original background seamlessly.",
"image_urls": ["https://example.com/watermarked-image.jpg"],
"mode": "max"
}'
清理皮肤瑕疵或照片伪影。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the skin blemishes and acne marks from this portrait photo. Keep the skin looking natural and maintain the original skin texture.",
"image_urls": ["https://example.com/portrait.jpg"],
"mode": "max"
}'
通过移除分散注意力的电线来清理风景和建筑照片。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all the power lines and electrical wires from this sunset cityscape photo. Make the sky look clean and unobstructed.",
"image_urls": ["https://example.com/cityscape-wires.jpg"],
"mode": "max"
}'
通过移除人群获得完美的空场地标照片。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all the tourists and people from this Eiffel Tower photo. I want it to look like an empty plaza with just the monument.",
"image_urls": ["https://example.com/eiffel-tower-crowded.jpg"],
"mode": "max"
}'
通过从个人照片中移除某人来挽救回忆。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person on the right side of this vacation photo. Fill in with the background scenery naturally so it looks like a solo travel photo.",
"image_urls": ["https://example.com/vacation-couple.jpg"],
"mode": "max"
}'
清理产品照片或带有不需要品牌标识的图像。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the brand logo from the t-shirt in this photo. Replace it with plain fabric that matches the shirt color and texture.",
"image_urls": ["https://example.com/branded-shirt.jpg"],
"mode": "max"
}'
从电子商务产品拍摄图中移除分散注意力的元素。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Clean up this product photo by removing the price tag, dust spots, and the reflection of the photographer in the surface. Make it look professional and ready for e-commerce.",
"image_urls": ["https://example.com/product-raw.jpg"],
"mode": "max"
}'
从照片中消除不需要的阴影。
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the harsh shadow cast by the photographer on the ground in this outdoor portrait. Make the lighting look natural and even.",
"image_urls": ["https://example.com/portrait-shadow.jpg"],
"mode": "max"
}'
使用 session_id 进行迭代移除和优化:
# First removal
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the car parked on the left side of this street photo",
"image_urls": ["https://example.com/street-scene.jpg"],
"session_id": "cleanup-project-001"
}'
# Second removal (same session)
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Now also remove the garbage bins near the building entrance",
"session_id": "cleanup-project-001"
}'
# Refinement (same session)
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "The area where the car was removed looks a bit blurry. Can you improve the texture to match the surrounding pavement better?",
"session_id": "cleanup-project-001"
}'
请求物体移除时,请在提示词中包含以下细节:
"Remove [object description] from [location in image].
Fill the area with [expected background/content].
Keep [elements to preserve] intact."
| 模式 | 最适合 | 速度 | 质量 |
|---|---|---|---|
max | 最终交付物、复杂移除、专业工作 | 较慢 | 最高 |
eco | 快速预览、简单移除、批量处理 | 较快 | 良好 |
推荐 : 对于复杂移除(人物、大型物体)使用 max 模式,对于简单清理(小瑕疵、灰尘点)使用 eco 模式。
| 错误 | 原因 | 解决方案 |
|---|---|---|
Failed to create prediction: HTTP 422 | 余额不足 | 在 eachlabs.ai 充值 |
| 内容策略违规 | 禁止的内容 | 查看内容指南 |
| 超时 | 复杂的生成过程 | 将客户端超时设置为至少10分钟 |
| 移除质量差 | 提示词模糊 | 更具体地描述位置和填充内容 |
物体移除操作可能需要时间,尤其是对于复杂场景。将您的 HTTP 客户端配置为至少 10 分钟的超时,以避免过早断开连接。
# Example with extended timeout
curl --max-time 600 -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all people from this crowded plaza photo",
"image_urls": ["https://example.com/crowded-plaza.jpg"],
"mode": "max"
}'
each-sense - 核心 API 文档image-edit - 通用图像编辑功能background-removal - 移除和替换背景每周安装量
84
代码仓库
GitHub 星标数
8
首次出现
2026年2月20日
安全审计
安装于
gemini-cli84
kimi-cli83
codex83
cursor83
opencode83
github-copilot83
Remove unwanted elements from photos using each::sense. This skill intelligently removes objects, people, text, watermarks, and imperfections while seamlessly filling the removed areas with contextually appropriate content.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person standing on the left side of this photo",
"image_urls": ["https://example.com/beach-photo.jpg"],
"mode": "max"
}'
Remove an unwanted person from a group photo or scenic shot.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person in the red shirt from this beach photo. Fill the area naturally with the ocean and sand background.",
"image_urls": ["https://example.com/beach-group.jpg"],
"mode": "max"
}'
Clean up photos by removing distracting objects.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the trash can and bench from the right side of this park landscape photo. Make it look like a clean natural scene.",
"image_urls": ["https://example.com/park-landscape.jpg"],
"mode": "max"
}'
Clean up images with unwanted text overlays or watermarks.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the watermark from the bottom right corner of this image. Restore the original background seamlessly.",
"image_urls": ["https://example.com/watermarked-image.jpg"],
"mode": "max"
}'
Clean up skin imperfections or photo artifacts.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the skin blemishes and acne marks from this portrait photo. Keep the skin looking natural and maintain the original skin texture.",
"image_urls": ["https://example.com/portrait.jpg"],
"mode": "max"
}'
Clean up landscape and architectural photos by removing distracting wires.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all the power lines and electrical wires from this sunset cityscape photo. Make the sky look clean and unobstructed.",
"image_urls": ["https://example.com/cityscape-wires.jpg"],
"mode": "max"
}'
Get that perfect empty landmark shot by removing crowds.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all the tourists and people from this Eiffel Tower photo. I want it to look like an empty plaza with just the monument.",
"image_urls": ["https://example.com/eiffel-tower-crowded.jpg"],
"mode": "max"
}'
Salvage memories by removing someone from personal photos.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the person on the right side of this vacation photo. Fill in with the background scenery naturally so it looks like a solo travel photo.",
"image_urls": ["https://example.com/vacation-couple.jpg"],
"mode": "max"
}'
Clean up product photos or images with unwanted branding.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the brand logo from the t-shirt in this photo. Replace it with plain fabric that matches the shirt color and texture.",
"image_urls": ["https://example.com/branded-shirt.jpg"],
"mode": "max"
}'
Remove distracting elements from e-commerce product shots.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Clean up this product photo by removing the price tag, dust spots, and the reflection of the photographer in the surface. Make it look professional and ready for e-commerce.",
"image_urls": ["https://example.com/product-raw.jpg"],
"mode": "max"
}'
Eliminate unwanted shadows from photos.
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the harsh shadow cast by the photographer on the ground in this outdoor portrait. Make the lighting look natural and even.",
"image_urls": ["https://example.com/portrait-shadow.jpg"],
"mode": "max"
}'
Use session_id for iterative removal and refinement:
# First removal
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove the car parked on the left side of this street photo",
"image_urls": ["https://example.com/street-scene.jpg"],
"session_id": "cleanup-project-001"
}'
# Second removal (same session)
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Now also remove the garbage bins near the building entrance",
"session_id": "cleanup-project-001"
}'
# Refinement (same session)
curl -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "The area where the car was removed looks a bit blurry. Can you improve the texture to match the surrounding pavement better?",
"session_id": "cleanup-project-001"
}'
When requesting object removal, include these details in your prompt:
"Remove [object description] from [location in image].
Fill the area with [expected background/content].
Keep [elements to preserve] intact."
| Mode | Best For | Speed | Quality |
|---|---|---|---|
max | Final deliverables, complex removals, professional work | Slower | Highest |
eco | Quick previews, simple removals, bulk processing | Faster | Good |
Recommendation : Use max mode for complex removals (people, large objects) and eco for simple cleanups (small blemishes, dust spots).
| Error | Cause | Solution |
|---|---|---|
Failed to create prediction: HTTP 422 | Insufficient balance | Top up at eachlabs.ai |
| Content policy violation | Prohibited content | Review content guidelines |
| Timeout | Complex generation | Set client timeout to minimum 10 minutes |
| Poor removal quality | Vague prompt | Be more specific about location and fill content |
Object removal operations can take time, especially for complex scenes. Configure your HTTP client with a minimum 10 minute timeout to avoid premature disconnections.
# Example with extended timeout
curl --max-time 600 -X POST https://sense.eachlabs.run/chat \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-H "Accept: text/event-stream" \
-d '{
"message": "Remove all people from this crowded plaza photo",
"image_urls": ["https://example.com/crowded-plaza.jpg"],
"mode": "max"
}'
each-sense - Core API documentationimage-edit - General image editing capabilitiesbackground-removal - Remove and replace backgroundsWeekly Installs
84
Repository
GitHub Stars
8
First Seen
Feb 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
gemini-cli84
kimi-cli83
codex83
cursor83
opencode83
github-copilot83
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,800 周安装