SDXL ControlNet Union · Image to Image
整合
模型 id
sdxl-controlnet-union/image-to-image
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/sdxl-controlnet-union/image-to-image?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/sdxl-controlnet-union/image-to-image?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sdxl-controlnet-union/image-to-image", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/zh-TW/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
--header "Authorization: Bearer $DOITONG_API_KEY"
# 2. Your agent calls the "run" tool with:
{
"model_id": "sdxl-controlnet-union/image-to-image",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
}
透過 Doitong API 呼叫 SDXL ControlNet Union · Image to Image 模型(sdxl-controlnet-union/image-to-image)。代理程式文件:https://doitong.com/zh-TW/developers/models/sdxl-controlnet-union/image-to-image.md
POST https://api.doitong.ru/v1/run/sdxl-controlnet-union/image-to-image?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
如果回應狀態為 "queued" 或 "running",請輪詢 GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20,直到狀態變為 "succeeded";檔案位於 outputs[].url。使用相同主體傳送 POST https://api.doitong.ru/v1/quote/sdxl-controlnet-union/image-to-image,可在執行前取得確切價格。
此請求: ≈$0.048 48 API 點數 · ≈ ₽5.12 在此頁面執行
您的新 API 金鑰。 僅會在此時顯示,且已填入下方的程式碼與 API 金鑰欄位。請妥善保密:切勿將其放入在瀏覽器中執行的程式碼。
建立請求
控制項是根據模型結構描述生成的。變更設定時,程式碼和價格會同步更新。
POST
/run/sdxl-controlnet-union/image-to-image?wait=20
報價 → $0.048
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/sdxl-controlnet-union/image-to-image?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}'
# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/sdxl-controlnet-union/image-to-image?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sdxl-controlnet-union/image-to-image", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])
# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run",
"arguments": {
"model_id": "sdxl-controlnet-union/image-to-image",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
},
"wait_seconds": 20
}
}
}
關於 SDXL ControlNet Union · Image to Image
使用 SDXL 基礎模型轉換起始圖像,並由提示詞和可選的 openpose、深度圖、teed、canny、normal、分割 控制圖像引導。每個控制輸入都有自己的前處理切換。`strength` 範圍為 0.05 到 1,`num_inference_steps` 為 1 到 70,每次呼叫最多可回傳 8 張圖像。可提供 LoRA 和嵌入向量,輸出格式為 jpeg 或 png。
參數
請傳送標準名稱或原生名稱其中之一,不要同時傳送兩者。 標準名稱
名稱類型
預設值允許值
說明
prompt必填
類型string
盡可能詳細地描述想要生成的圖像,以取得最佳結果。
controlnet_conditioning_scale選填
類型number
預設值0.5
0 – 1
ControlNet 套用的條件強度。
image_url必填
image
類型url · image
以 URL 提供的生成起始圖像。
negative_prompt選填
類型string
預設值
指定不需要圖像細節的負面提示詞。可排除色彩、物件、景物或更細微的特徵與品質,例如鬍鬚、模糊或低解析度。
image_size選填
類型object
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
輸出尺寸;未提供尺寸時,會根據控制圖像自動決定。
num_inference_steps選填
類型integer
預設值35
1 – 70
要執行的推論步數。
guidance_scale選填
類型number
預設值7.5
0 – 20
圖像選取的提示詞遵循強度,以 CFG (Classifier Free Guidance) 表示。
strength選填
類型number
預設值0.95
0.05 – 1
生成圖像與初始圖像之間的相似程度。
seed選填
類型integer | null
用於在 Stable Diffusion 中重現圖像的種子。只要模型版本、提示詞和種子保持不變,每次執行都能精確重現圖像。
num_images選填
num_outputs
類型integer
預設值1
1 – 8
請求生成的圖像數量。
loras選填
類型object[]
預設值[]
選用的 LoRA 權重,以清單形式提供。
loras[].force選填
類型boolean
預設值false
是否強制使用嵌入:true 表示必須使用。
loras[].path必填
類型string
LoRA 權重來源,可以是解析至 safetensors 權重的 HF 模型識別碼,或由 URL 或路徑定位的 safetensors 檔案。
loras[].scale選填
類型number
預設值1
0 – 1
合併至基礎模型前套用至 LoRA 權重的倍數。
embeddings選填
類型object[]
預設值[]
選用的嵌入,以清單形式提供。
embeddings[].path必填
類型string
由 URL 或檔案路徑指定的嵌入權重。
embeddings[].tokens選填
類型string[]
嵌入 Token 清單;省略時會自動命名:嵌入檔案中的每個向量都會從序列 <s0>、<s1>、... 中取得一個 Token。
enable_safety_checker選填
類型boolean
預設值true
安全檢查器啟用狀態;true 會啟用檢查。
safety_checker_version選填
類型enum
預設值v1
v1v2
在自訂 ViT 安全檢查器(`v2`)與 CompVis 檢查器(`v1`,預設值)之間選擇。
expand_prompt選填
類型boolean
預設值false
提示詞擴展;為 true 時啟用額外提示詞。
format選填
類型enum
預設值jpeg
jpegpng
生成圖像的檔案格式。
request_id選填
類型string
預設值
用於將回應與產生該回應之請求建立關聯的請求識別碼。
preserve_aspect_ratio選填
類型boolean
預設值false
設為 true 時,即使生成圖像尺寸超過限制,也會保留其長寬比。若要在生成後透過裁切取得正確比例,請將 crop_output 設為 True。不可被 32 整除的寬度或高度值仍會四捨五入至最接近的 32 倍數,且此調整預設不會保留長寬比。
crop_output選填
類型boolean
預設值false
設為 true 時,將生成的輸出裁切為正確長寬比。
openpose_image_url選填
類型url · image
指向控制圖像的 URL。
openpose_preprocess選填
類型boolean
預設值true
控制 openpose 圖像的前處理。
depth_image_url選填
類型url · image
指向控制圖像的 URL。
depth_preprocess選填
類型boolean
預設值true
控制深度圖像的前處理。
teed_image_url選填
類型url · image
指向控制圖像的 URL。
teed_preprocess選填
類型boolean
預設值true
控制 teed 圖像的前處理。
canny_image_url選填
類型url · image
指向控制圖像的 URL。
canny_preprocess選填
類型boolean
預設值true
控制 canny 圖像的前處理。
normal_image_url選填
類型url · image
指向控制圖像的 URL。
normal_preprocess選填
類型boolean
預設值true
控制 normal 圖像的前處理。
segmentation_image_url選填
類型url · image
指向控制圖像的 URL。
segmentation_preprocess選填
類型boolean
預設值true
控制分割圖像的前處理。
必填
標準名稱,也可使用
檔案參數接受公開的 https:// URL、最大 10 MB 的 data: URI,或上傳檔案的 file_url。 檔案
輸出
GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "sdxl-controlnet-union/image-to-image",
"status": "succeeded",
"created_at": "2026-10-20T12:00:00Z",
"started_at": "2026-10-20T12:00:02Z",
"completed_at": "2026-10-20T12:00:09Z",
"queue_position": null,
"cost": {
"credits": 48,
"usd": "0.048",
"charged": 48,
"refunded": 0
},
"input": {
"image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
},
"output": {
"images": [
{
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"width": 1024,
"height": 768,
"content_type": "image/jpeg"
}
],
"timings": {},
"seed": 42,
"has_nsfw_concepts": [
false
],
"prompt": "string"
},
"outputs": [
{
"type": "image",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
"content_type": "image/jpeg",
"file_size": 1843200,
"width": 1024,
"height": 768,
"stored": true
}
],
"error": null,
"metrics": {
"inference_seconds": 6.8
},
"urls": {
"self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
"cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
}
}
您的檔案,由您選擇每個 outputs[].url 都是儲存空間中的副本:可永久保留(按 GB-月計費),或免費保留 7 天;可透過帳戶設定或 ?storage= 設定。
所有模型使用相同結構圖片、影片和音訊皆包含 type、url、content_type、width、height 和 duration。output 是模型自己的結果物件。
輸出欄位
- images
- array of object {url, width, height, content_type}生成圖像的檔案資訊。
- timings
- object
- seed
- integer圖像生成種子;若輸入未提供種子,則包含隨機選取的值,否則會重複提供的值。
- has_nsfw_concepts
- array of boolean指出生成的圖像中是否出現 NSFW 概念。
- prompt
- string圖像生成期間使用的提示詞。
其他 SDXL ControlNet Union 變體
更多模型:圖像編輯
給 AI 代理程式:此頁面的 Markdown 位於 https://doitong.com/zh-TW/developers/models/sdxl-controlnet-union/image-to-image.md. 所有模型與指南: https://doitong.com/developers/llms.txt






