API 协议
POST · Image editing
直接答案POST /v1/images/edits。包含鉴权、请求参数、三种语言示例、结果判定与错误处理。
更新 · 审核信息
OpenFox · Image editing
POST https://api.openfox.vip/v1/images/edits
Model ID: YOUR_MODEL_ID
Authentication
Authorization: Bearer $OPENFOX_API_KEY
Create a model API key in API Keys. Dashboard sessions and personal access tokens are not model API credentials.
Keep credentials in environment variables on your server. Do not paste real keys, cookies or account records into this guide.
Request parameters
- model (body, string, Required): See schema details.
- prompt (body, string, Required): See schema details.
- image (body, string, Required): A real local image supported by the model. Set OPENFOX_IMAGE_PATH.
- mask (body, string, Optional): Optional mask; format, transparency and size depend on the model.
- n (body, integer, Optional): Gateway limit does not imply model support.
- size (body, string, Optional): Model-specific output dimensions.
Example values are not server defaults. Model-specific parameter support must be confirmed for the selected channel.
Model and channel limitations
This example uploads one local image using multipart. File formats, masks, image count and size limits depend on the selected model and adapter. The HTTP library must set the multipart boundary.
Request example
Run one language example only. Creation requests may be charged; do not run every example or retry automatically.
Set OPENFOX_REQUEST_ID from the original X-Request-Id when recovering images. Set OPENFOX_TASK_ID from a real task creation response when querying tasks.
curl
: "${OPENFOX_IMAGE_PATH:?Set a real image path}"
# Bash / WSL; curl 7.76+ and jq. Run ONE language example, not all of them.
umask 077
RESULT=$(mktemp)
trap 'rm -f "$RESULT"' EXIT
: "${OPENFOX_API_KEY:?Set OPENFOX_API_KEY}"
curl --silent --show-error --fail-with-body --max-time 180 'https://api.openfox.vip/v1/images/edits' \
-H "Authorization: Bearer $OPENFOX_API_KEY" \
-F "image=@$OPENFOX_IMAGE_PATH" \
--form-string 'model=YOUR_MODEL_ID' \
--form-string 'prompt=Add soft morning light to this image.' \
--output "$RESULT" || exit 1
jq -e 'type == "object" and (.error | not) and (.success != false) and (.code != false)' "$RESULT" >/dev/null || exit 1
# HTTP/business envelope checked only. Complete result validation is required:
# Upload a real local image with an automatically generated multipart boundary. Decode and verify the returned images before saving.
# Use the Python or JavaScript example in this guide for result processing.
python
# Python 3.10+; install: pip install httpx pillow
import asyncio, json, os
from urllib.parse import quote, urlparse
import httpx
async def main():
url = "https://api.openfox.vip/v1/images/edits"
headers = {}
headers["Authorization"] = "Bearer " + os.environ["OPENFOX_API_KEY"]
params = {}
from pathlib import Path
image_path = Path(os.environ['OPENFOX_IMAGE_PATH'])
if image_path.stat().st_size > 20_000_000:
raise RuntimeError('Image too large')
files = {'image': (image_path.name, image_path.read_bytes())}
async with httpx.AsyncClient(timeout=30, follow_redirects=False) as client:
async def read(target, method='GET', payload=None):
response = await client.request(method, target, headers=headers, params=params, data=payload, files=files)
response.raise_for_status()
value = response.json()
if not isinstance(value, dict) or value.get('error') or value.get('success') is False or value.get('code') is False:
raise RuntimeError('API business error')
return value
data = await read(url, "POST", json.loads("{\"model\":\"YOUR_MODEL_ID\",\"prompt\":\"Add soft morning light to this image.\"}"))
import base64, io
from pathlib import Path
from PIL import Image
Image.MAX_IMAGE_PIXELS = 20_000_000
items = data.get('data')
if not isinstance(items, list) or not items:
raise RuntimeError('No images')
for index, item in enumerate(items):
if item.get('b64_json'):
if len(item['b64_json']) > 28_000_000:
raise RuntimeError('Image too large')
image_bytes = base64.b64decode(item['b64_json'], validate=True)
else:
asset = urlparse(item.get('url', ''))
if asset.scheme != 'https' or not asset.netloc or asset.username or asset.password:
raise RuntimeError('Unsafe image URL')
image_bytes = bytearray()
# Separate client: no API key, cookies or redirects.
async with httpx.AsyncClient(timeout=30, follow_redirects=False) as download_client:
async with download_client.stream('GET', asset.geturl()) as download:
download.raise_for_status()
async for chunk in download.aiter_bytes():
image_bytes.extend(chunk)
if len(image_bytes) > 20_000_000:
raise RuntimeError('Image too large')
if not image_bytes or len(image_bytes) > 20_000_000:
raise RuntimeError('Invalid image size')
with Image.open(io.BytesIO(image_bytes)) as image:
if image.width * image.height > 20_000_000:
raise RuntimeError('Image dimensions too large')
image.load()
image.save(Path('openfox-image-' + str(index) + '.png'))
print('Saved verified image', index)
async def bounded():
await asyncio.wait_for(main(), timeout=180)
asyncio.run(bounded())
javascript
// Node.js 20+; save as example.mjs and run: node example.mjs
// Install: npm install sharp
const controller = new AbortController();
const timer = setTimeout(() => controller.abort(), 180000);
const signal = controller.signal;
try {
const url = new URL("https://api.openfox.vip/v1/images/edits");
const { readFile, stat } = await import('node:fs/promises');
const { basename } = await import('node:path');
const imagePath = process.env.OPENFOX_IMAGE_PATH;
if (!imagePath || (await stat(imagePath)).size > 20_000_000) throw Error('Set an image path below 20MB');
const form = new FormData();
form.append('image', new Blob([await readFile(imagePath)]), basename(imagePath));
for (const [key, value] of Object.entries({"model":"YOUR_MODEL_ID","prompt":"Add soft morning light to this image."})) form.append(key, String(value));
const headers = {};
if (!process.env.OPENFOX_API_KEY) throw Error('Set OPENFOX_API_KEY');
headers["Authorization"] = "Bearer " + process.env.OPENFOX_API_KEY;
const read = async (target, method = 'GET', payload) => {
const response = await fetch(target, { method, headers, signal, redirect: 'error', body: payload === undefined ? undefined : payload });
if (!response.ok) throw Error('HTTP ' + response.status);
const data = await response.json();
if (!data || typeof data !== 'object' || data.error || data.success === false || data.code === false) throw Error('API business error');
return data;
};
let data = await read(url, "POST", form);
if (!Array.isArray(data.data) || !data.data.length) throw Error('No images');
const { default: sharp } = await import('sharp');
const { writeFile } = await import('node:fs/promises');
for (const [index, item] of data.data.entries()) {
let bytes;
if (typeof item.b64_json === 'string' && item.b64_json.length) {
if (item.b64_json.length > 28_000_000 || !/^[A-Za-z0-9+/]*={0,2}$/.test(item.b64_json)) throw Error('Invalid or oversized Base64');
bytes = Buffer.from(item.b64_json, 'base64');
if (bytes.toString('base64').replace(/=+$/, '') !== item.b64_json.replace(/=+$/, '')) throw Error('Invalid Base64');
} else {
const asset = new URL(item.url);
if (asset.protocol !== 'https:' || asset.username || asset.password) throw Error('Unsafe image URL');
// Fresh request: NO Authorization header, cookies or redirects.
const download = await fetch(asset, { signal, redirect: 'error' });
if (!download.ok || !download.body) throw Error('Image download failed');
const chunks = []; let length = 0;
for await (const chunk of download.body) {
length += chunk.length;
if (length > 20_000_000) { controller.abort(); throw Error('Image too large'); }
chunks.push(chunk);
}
bytes = Buffer.concat(chunks);
}
if (!bytes.length || bytes.length > 20_000_000) throw Error('Invalid image size');
const image = sharp(bytes, { limitInputPixels: 20_000_000 });
await image.clone().raw().toBuffer(); // Decode actual pixels, not just HTTP or metadata.
await writeFile('openfox-image-' + index + '.png', await image.png().toBuffer());
console.log('Saved verified image', index);
}
} finally { clearTimeout(timer); }
Results and success criteria
Upload a real local image with an automatically generated multipart boundary. Decode and verify the returned images before saving.
Error handling
Check both HTTP status and business errors. A timeout does not prove the operation failed. Do not automatically retry creation requests; inspect the original request or usage first.
401/403: check credentials, scopes, model permissions and IP rules. 429: check quota and rate limits. 5xx: preserve a non-secret request ID and contact support.
Python and JavaScript share a 180-second network deadline. Read-only polling is bounded. Unknown or failure states stop the flow. Image decoding is local CPU work with byte and pixel limits.
Uploads, downloads and related endpoints
Only the image editing example uploads a local file. Set OPENFOX_IMAGE_PATH to a supported image. Other examples do not upload files. Download external results without platform credentials. Task artifacts require format-specific verification.
- https://api.openfox.vip/docs?operation=images
Full request schema
{
"parameters": [],
"requestBody": {
"required": true,
"content": {
"multipart/form-data": {
"schema": {
"type": "object",
"required": [
"model",
"prompt",
"image"
],
"properties": {
"model": {
"type": "string"
},
"prompt": {
"type": "string"
},
"image": {
"type": "string",
"format": "binary",
"description": "A real local image supported by the model. Set OPENFOX_IMAGE_PATH."
},
"mask": {
"type": "string",
"format": "binary",
"description": "Optional mask; format, transparency and size depend on the model."
},
"n": {
"type": "integer",
"description": "Gateway limit does not imply model support."
},
"size": {
"type": "string",
"description": "Model-specific output dimensions."
}
}
}
}
}
}
}
Sources and verification
docs/openapi/relay.json · relay/image_handler.go, relaykit/dto/openai_image.go · 2026-11-03
SHA-256: aeee6c35a35b2eaced964401f3826f369ad7ac8985c17989dcbbe08337d9fa01
source-reviewed; upstream-not-tested; source-reviewed; provider extensions conditional
Source review is not upstream business verification. Availability and billing depend on your account, group and channel.
适用场景
- getting-started
- troubleshooting
API 协议
/v1/images/edits
常见问题
这里是否保证模型可调用?
不保证。请在模型广场核对精确型号、账号分组与端点权限。
示例是否使用真实密钥?
不使用。请在自己的服务端设置环境变量,并将 YOUR_MODEL_ID 替换为可用的精确模型 ID。
接口超时可以立即重试吗?
创建请求不应自动重试。先核对请求编号、任务状态和用量,避免重复收费。
关联指南
官方来源
- OpenFox API 官方