> ## Documentation Index
> Fetch the complete documentation index at: https://apidoc.cometapi.com/llms.txt
> Use this file to discover all available pages before exploring further.
# إنشاء تعديلات صور SeedEdit
> استخدم CometAPI POST /v1/images/edits لتحرير صور SeedEdit باستخدام مدخلات JSON، وعمليات الرفع multipart، والتعديلات الموجّهة عبر Prompt، مع أقنعة اختيارية.
استخدم مسار `POST /v1/images/edits` المتوافق مع OpenAI من CometAPI لتشغيل تحرير صور SeedEdit. تقبل نقطة النهاية هذه مراجع الصور بصيغة JSON أو عمليات رفع الملفات بنمط multipart، ويمكنها تطبيق تغييرات موجّهة عبر Prompt مع قناع اختياري.
للاطلاع على model ID المتاحة، راجع [صفحة Models](/ar/overview/models) أو استعلم عن `/v1/models`. ولمعرفة تفاصيل معلمات المزوّد، راجع [توثيق VolcEngine SeedEdit](https://www.volcengine.com/docs/82379/1666946).
## اختر شكل طلب التعديل
* تعديل JSON: أرسل `model` و`image` و`prompt` وعناصر تحكم اختيارية مثل `size` و`response_format` و`watermark`.
* رفع Multipart: أرسل الحقول نفسها كأجزاء form وارفع `image` كملف.
* تعديل باستخدام قناع: أضف `mask` كـ data URI أو عنوان URL عام عبر HTTPS أو ملف مرفوع. استخدم قناع PNG عالي التباين لتحديد منطقة التعديل.
استخدم `2K` أو `4K` أو `1K` أو قيمة `WIDTHxHEIGHT` يدعمها model من أجل `size`. احذف `size` عندما تريد القيمة الافتراضية للمسار.
## أرسل مدخلات الصور
في طلبات JSON، استخدم `data:image/png;base64,YOUR_BASE64_IMAGE` أو عنوان URL عامًا عبر HTTPS يمكن للمزوّد جلبه. أما في طلبات multipart، فارفع `source.png` أو أي ملف صورة مدعوم آخر مباشرةً.
## اقرأ عناوين URL الناتجة
القيمة `url` المُعادة هي رابط موقّع لتخزين الكائنات، وقد تحتوي على `&` و`%` ومحارف خاصة أخرى. استخرج عنوان URL من JSON بعد تحليله بدلًا من نسخ سطر جزئي من الطرفية. في أمثلة shell، يحافظ `jq -r '.data[]?.url'` على عنوان URL الموقّع بالكامل.
## OpenAPI
````yaml api/openapi/image/seededit-seedream/post-bytedance-image-editing.openapi.json POST /v1/images/edits
openapi: 3.1.0
info:
title: SeedEdit image editing API
version: 1.0.0
servers:
- url: https://api.cometapi.com
security:
- bearerAuth: []
paths:
/v1/images/edits:
post:
summary: Create SeedEdit image edits
operationId: bytedance_image_editing
requestBody:
required: true
content:
application/json:
schema:
type: object
description: Parameters for SeedEdit image editing with JSON image inputs.
required:
- model
- image
- prompt
properties:
model:
type: string
description: >-
SeedEdit model ID to use. Query `/v1/models` or open the
[Models page](/overview/models) for available image editing
model IDs.
default: doubao-seededit-3-0-i2i-250628
image:
type: string
description: >-
Source image to edit as a public HTTPS URL or a data URI
such as `data:image/png;base64,YOUR_BASE64_IMAGE`. Use JPEG
or PNG input and keep the file within the route size limit.
default: data:image/png;base64,YOUR_BASE64_IMAGE
mask:
type: string
description: >-
Optional mask image as a public HTTPS URL or data URI. Use a
high-contrast PNG mask to mark the region that should
receive the edit.
default: data:image/png;base64,YOUR_BASE64_MASK
prompt:
type: string
description: >-
Instruction describing the desired edit, such as `Change the
red square into a blue square and keep the background
unchanged`.
default: >-
Change the red square into a blue square and keep the
background unchanged.
response_format:
type: string
description: >-
Response image format. Use `url` for a temporary signed
image URL, or `b64_json` when you need base64 image data in
the response.
default: url
enum:
- url
- b64_json
size:
type: string
description: >-
Output resolution. Use a tier such as `1K`, `2K`, or `4K`,
or a model-supported `WIDTHxHEIGHT` value such as
`2048x2048`. Omit the field to use the route default.
default: 2K
seed:
type: integer
description: >-
Optional random seed for reproducible attempts on model
versions that support seeding. Use `-1` or omit the field
for a random seed.
minimum: -1
maximum: 2147483647
default: -1
guidance_scale:
type: number
description: >-
Optional prompt-adherence control for model versions that
support it. Higher values can follow the prompt more closely
but may reduce naturalness.
minimum: 1
maximum: 10
watermark:
type: boolean
description: >-
When `true`, requests a visible AI-generated watermark on
the output image. Set `false` when your workflow handles
disclosure separately.
default: false
default:
model: doubao-seededit-3-0-i2i-250628
image: data:image/png;base64,YOUR_BASE64_IMAGE
prompt: >-
Change the red square into a blue square and keep the
background unchanged.
response_format: url
size: 2K
watermark: false
examples:
Image data URI (JSON):
summary: Edit an image supplied as a data URI
value:
model: doubao-seededit-3-0-i2i-250628
image: data:image/png;base64,YOUR_BASE64_IMAGE
prompt: >-
Change the red square into a blue square and keep the
background unchanged.
response_format: url
size: 2K
watermark: false
Masked edit (JSON):
summary: Edit an image with a mask supplied as a data URI
value:
model: doubao-seededit-3-0-i2i-250628
image: data:image/png;base64,YOUR_BASE64_IMAGE
mask: data:image/png;base64,YOUR_BASE64_MASK
prompt: >-
Change only the masked red square into a blue square and
keep the background unchanged.
response_format: url
size: 2K
watermark: false
multipart/form-data:
schema:
type: object
description: Parameters for SeedEdit image editing with uploaded image files.
required:
- model
- image
- prompt
properties:
model:
type: string
description: >-
SeedEdit model ID to use. Query `/v1/models` or open the
[Models page](/overview/models) for available image editing
model IDs.
default: doubao-seededit-3-0-i2i-250628
image:
type: string
format: binary
description: >-
Source image file to edit. Use JPEG or PNG input and keep
the file within the route size limit.
mask:
type: string
format: binary
description: >-
Optional mask image file. Use a high-contrast PNG mask to
mark the region that should receive the edit.
prompt:
type: string
description: >-
Instruction describing the desired edit, such as `Change the
red square into a blue square and keep the background
unchanged`.
default: >-
Change the red square into a blue square and keep the
background unchanged.
response_format:
type: string
description: >-
Response image format. Use `url` for a temporary signed
image URL, or `b64_json` when you need base64 image data in
the response.
default: url
enum:
- url
- b64_json
size:
type: string
description: >-
Output resolution. Use a tier such as `1K`, `2K`, or `4K`,
or a model-supported `WIDTHxHEIGHT` value such as
`2048x2048`. Omit the field to use the route default.
default: 2K
seed:
type: integer
description: >-
Optional random seed for reproducible attempts on model
versions that support seeding. Use `-1` or omit the field
for a random seed.
minimum: -1
maximum: 2147483647
default: -1
guidance_scale:
type: number
description: >-
Optional prompt-adherence control for model versions that
support it. Higher values can follow the prompt more closely
but may reduce naturalness.
minimum: 1
maximum: 10
watermark:
type: boolean
description: >-
When `true`, requests a visible AI-generated watermark on
the output image. Set `false` when your workflow handles
disclosure separately.
default: false
responses:
'200':
description: Successful response
content:
application/json:
schema:
type: object
required:
- created
- data
properties:
created:
type: integer
description: >-
Unix timestamp in seconds when the image response was
created.
data:
type: array
description: Edited image results.
items:
type: object
properties:
url:
type: string
description: >-
Temporary signed URL for the edited image. Save or
download the image before the URL expires.
b64_json:
type: string
description: >-
Base64-encoded image data when `response_format` is
`b64_json`.
size:
type: string
description: >-
Pixel dimensions of the edited image when returned
by the model, such as `2048x2048`.
usage:
type: object
description: >-
Usage information for the request. Fields vary by model
and route.
properties:
output_tokens:
type: integer
description: >-
Image output tokens charged for the edited image data,
when reported.
total_tokens:
type: integer
description: Total tokens reported for the request.
prompt_tokens:
type: integer
description: Prompt tokens reported by the route, when available.
completion_tokens:
type: integer
description: >-
Completion tokens reported by the route, when
available.
x-codeSamples:
- lang: Shell
label: Image data URI (JSON)
source: |
curl -s https://api.cometapi.com/v1/images/edits \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seededit-3-0-i2i-250628",
"image": "data:image/png;base64,YOUR_BASE64_IMAGE",
"prompt": "Change the red square into a blue square and keep the background unchanged.",
"response_format": "url",
"size": "2K",
"watermark": false
}' | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Image data URI (JSON)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/edits",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={"model": "doubao-seededit-3-0-i2i-250628", "image": "data:image/png;base64,YOUR_BASE64_IMAGE", "prompt": "Change the red square into a blue square and keep the background unchanged.", "response_format": "url", "size": "2K", "watermark": False},
timeout=180,
)
response.raise_for_status()
result = response.json()
for image in result.get("data", []):
print(image.get("url") or image.get("b64_json"))
- lang: JavaScript
label: Image data URI (JSON)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/edits", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "doubao-seededit-3-0-i2i-250628",
"image": "data:image/png;base64,YOUR_BASE64_IMAGE",
"prompt": "Change the red square into a blue square and keep the background unchanged.",
"response_format": "url",
"size": "2K",
"watermark": false
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
for (const image of result.data ?? []) {
console.log(image.url ?? image.b64_json);
}
- lang: Shell
label: Masked edit (JSON)
source: |
curl -s https://api.cometapi.com/v1/images/edits \
-H "Authorization: Bearer $COMETAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seededit-3-0-i2i-250628",
"image": "data:image/png;base64,YOUR_BASE64_IMAGE",
"mask": "data:image/png;base64,YOUR_BASE64_MASK",
"prompt": "Change only the masked red square into a blue square and keep the background unchanged.",
"response_format": "url",
"size": "2K",
"watermark": false
}' | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Masked edit (JSON)
source: |
import os
import requests
response = requests.post(
"https://api.cometapi.com/v1/images/edits",
headers={
"Authorization": "Bearer " + os.environ["COMETAPI_KEY"],
"Content-Type": "application/json",
},
json={"model": "doubao-seededit-3-0-i2i-250628", "image": "data:image/png;base64,YOUR_BASE64_IMAGE", "mask": "data:image/png;base64,YOUR_BASE64_MASK", "prompt": "Change only the masked red square into a blue square and keep the background unchanged.", "response_format": "url", "size": "2K", "watermark": False},
timeout=180,
)
response.raise_for_status()
result = response.json()
for image in result.get("data", []):
print(image.get("url") or image.get("b64_json"))
- lang: JavaScript
label: Masked edit (JSON)
source: >
const response = await
fetch("https://api.cometapi.com/v1/images/edits", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.COMETAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "doubao-seededit-3-0-i2i-250628",
"image": "data:image/png;base64,YOUR_BASE64_IMAGE",
"mask": "data:image/png;base64,YOUR_BASE64_MASK",
"prompt": "Change only the masked red square into a blue square and keep the background unchanged.",
"response_format": "url",
"size": "2K",
"watermark": false
}),
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
for (const image of result.data ?? []) {
console.log(image.url ?? image.b64_json);
}
- lang: Shell
label: Upload file
source: |
curl -s https://api.cometapi.com/v1/images/edits \
-H "Authorization: Bearer $COMETAPI_KEY" \
-F model="doubao-seededit-3-0-i2i-250628" \
-F prompt="Change the red square into a blue square and keep the background unchanged." \
-F response_format="url" \
-F size="2K" \
-F watermark="false" \
-F image=@source.png | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Upload file
source: |
import os
import requests
try:
image_file = open("source.png", "rb")
response = requests.post(
"https://api.cometapi.com/v1/images/edits",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
data={"model": "doubao-seededit-3-0-i2i-250628", "prompt": "Change the red square into a blue square and keep the background unchanged.", "response_format": "url", "size": "2K", "watermark": "false"},
files={
"image": image_file
},
timeout=180,
)
response.raise_for_status()
result = response.json()
print(result["data"][0].get("url") or result["data"][0].get("b64_json"))
finally:
image_file.close()
- lang: JavaScript
label: Upload file
source: >
import { readFile } from "node:fs/promises";
const form = new FormData();
form.append("model", "doubao-seededit-3-0-i2i-250628");
form.append("prompt", "Change the red square into a blue square and
keep the background unchanged.");
form.append("response_format", "url");
form.append("size", "2K");
form.append("watermark", "false");
form.append("image", new Blob([await readFile("source.png")], {
type: "image/png" }), "source.png");
const response = await
fetch("https://api.cometapi.com/v1/images/edits", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}` },
body: form,
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
console.log(result.data[0].url ?? result.data[0].b64_json);
- lang: Shell
label: Masked upload
source: |
curl -s https://api.cometapi.com/v1/images/edits \
-H "Authorization: Bearer $COMETAPI_KEY" \
-F model="doubao-seededit-3-0-i2i-250628" \
-F prompt="Change only the masked red square into a blue square and keep the background unchanged." \
-F response_format="url" \
-F size="2K" \
-F watermark="false" \
-F image=@source.png \
-F mask=@mask.png | jq -r '.data[]? | .url // .b64_json'
- lang: Python
label: Masked upload
source: |
import os
import requests
try:
image_file = open("source.png", "rb")
mask_file = open("mask.png", "rb")
response = requests.post(
"https://api.cometapi.com/v1/images/edits",
headers={"Authorization": "Bearer " + os.environ["COMETAPI_KEY"]},
data={"model": "doubao-seededit-3-0-i2i-250628", "prompt": "Change only the masked red square into a blue square and keep the background unchanged.", "response_format": "url", "size": "2K", "watermark": "false"},
files={
"image": image_file,
"mask": mask_file
},
timeout=180,
)
response.raise_for_status()
result = response.json()
print(result["data"][0].get("url") or result["data"][0].get("b64_json"))
finally:
image_file.close()
mask_file.close()
- lang: JavaScript
label: Masked upload
source: >
import { readFile } from "node:fs/promises";
const form = new FormData();
form.append("model", "doubao-seededit-3-0-i2i-250628");
form.append("prompt", "Change only the masked red square into a blue
square and keep the background unchanged.");
form.append("response_format", "url");
form.append("size", "2K");
form.append("watermark", "false");
form.append("image", new Blob([await readFile("source.png")], {
type: "image/png" }), "source.png");
form.append("mask", new Blob([await readFile("mask.png")], { type:
"image/png" }), "mask.png");
const response = await
fetch("https://api.cometapi.com/v1/images/edits", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.COMETAPI_KEY}` },
body: form,
});
if (!response.ok) {
throw new Error(await response.text());
}
const result = await response.json();
console.log(result.data[0].url ?? result.data[0].b64_json);
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication. Use your CometAPI key.
````