AI Object Remover — Agent Skill
AI Object Remover — Agent Skill
Remove unwanted objects from images using the AI Pass API. This skill uses Gemini's image editing model via chat completions.
Setup
- Create an account at aipass.one
- Get your API key from the Developer Dashboard → API Keys
- Set
$AIPASS_API_KEYin your environment
Usage
result = remove_object("photo.jpg", "Remove the person on the left")
# Returns edited image as base64
API Details
- Endpoint:
POST https://aipass.one/apikey/v1/chat/completions - Model:
gemini/gemini-3-pro-image-preview - Auth:
Authorization: Bearer $AIPASS_API_KEY
Related
Skill File
import requests
import os
import base64
AIPASS_API_KEY = os.environ["AIPASS_API_KEY"]
BASE_URL = "https://aipass.one/apikey/v1"
def remove_object(image_path, instruction):
"""Remove objects from an image using AI.
Args:
image_path: Path to the image file
instruction: What to remove (e.g. "Remove the person on the left")
Returns:
str: The AI response (base64 image or description)
"""
with open(image_path, "rb") as f:
b64 = base64.b64encode(f.read()).decode()
ext = image_path.rsplit(".", 1)[-1].lower()
mime = {"png": "image/png", "jpg": "image/jpeg", "jpeg": "image/jpeg", "webp": "image/webp"}.get(ext, "image/png")
r = requests.post(
f"{BASE_URL}/chat/completions",
headers={
"Authorization": f"Bearer {AIPASS_API_KEY}",
"Content-Type": "application/json"
},
json={
"model": "gemini/gemini-3-pro-image-preview",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": f"Remove the following from this image: {instruction}. Fill the area naturally."},
{"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}}
]
}]
}
)
return r.json()["choices"][0]["message"]["content"]
Download Skill File