SDXL ControlNet Union · Image to Image

Unganisha

Kitambulisho cha modeli 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/sw/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"
  }
}

Piga modeli ya SDXL ControlNet Union · Image to Image (sdxl-controlnet-union/image-to-image) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/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"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/sdxl-controlnet-union/image-to-image yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: ≈$ 0.048 salio za API 48 · ≈ ₽ 5.16 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Stability AI Uhariri wa Picha #diffusion#controlnet#composition

SDXL ya picha hadi picha yenye mwongozo wa ControlNet nyingi kutoka picha za udhibiti za mkao, kina, kingo, normal au ugawaji wa sehemu

OpenAPI Markdown

Stability AI · Picha

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika

Eleza picha unayotaka kuzalisha kwa maelezo mengi iwezekanavyo ili kupata matokeo bora.

image •inahitajika image_url

Dondosha faili, au

Picha ya kuanzia uzalishaji, iliyotolewa kupitia URL.

image_size

Vipimo vya tokeo, vinavyobainishwa kiotomatiki kutoka kwenye picha ya udhibiti wakati hakuna ukubwa uliotolewa.

num_outputs num_images chaguomsingi 1

Idadi ya picha iliyoombwa kwa uzalishaji.

Ya kina negative_prompt · openpose_image_url · depth_image_url · teed_image_url · canny_image_url · normal_image_url · segmentation_image_url · safety_checker_version · format · request_id · controlnet_conditioning_scale · num_inference_steps · guidance_scale · strength · seed · enable_safety_checker · expand_prompt · preserve_aspect_ratio · crop_output · openpose_preprocess · depth_preprocess · teed_preprocess · canny_preprocess · normal_preprocess · segmentation_preprocess · loras · embeddings

negative_prompt chaguomsingi

Kidokezo hasi kinachobainisha maelezo ya picha yasiyotakiwa. Kinaweza kuondoa rangi, vitu, mandhari au vipengele na sifa ndogo, kama vile masharubu, ukungu au mwonekano wa chini.

openpose_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

depth_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

teed_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

canny_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

normal_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

segmentation_image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya udhibiti.

safety_checker_version chaguomsingi v1

Chagua kati ya kikagua usalama maalum cha ViT (`v2`) na kikagua cha CompVis (`v1`, chaguomsingi).

format chaguomsingi jpeg

Muundo wa faili wa picha inayotokana.

request_id chaguomsingi

Kitambulishi cha ombi cha kuhusisha jibu na ombi lililolitengeneza.

controlnet_conditioning_scale chaguomsingi 0.5

Nguvu ya conditioning inayotumiwa na ControlNet.

num_inference_steps chaguomsingi 35

Idadi ya hatua za inference zitakazoendeshwa.

guidance_scale chaguomsingi 7.5

Nguvu ya kufuata kidokezo kwa uteuzi wa picha, iliyoonyeshwa kama CFG (Classifier Free Guidance).

strength chaguomsingi 0.95

Kiwango cha ufanano kati ya picha iliyozalishwa na picha ya awali.

seed

Mbegu ya kurudia picha katika Stable Diffusion. Picha inaweza kurudiwa kwa usahihi kila uendeshaji kwa kuweka toleo la modeli, kidokezo na mbegu bila kubadilika.

loras chaguomsingi []

Uzani wa LoRA uliochaguliwa kutumika, uliotolewa kama orodha.

embeddings chaguomsingi []

Embeddings zilizochaguliwa kutumika, zilizotolewa kama orodha.

POST /run/sdxl-controlnet-union/image-to-image?wait=20 makadirio → $ 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
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu SDXL ControlNet Union · Image to Image

Hubadilisha picha ya kuanzia kwa kutumia msingi wa SDXL unaoongozwa na kidokezo na picha za udhibiti za hiari za openpose, ramani ya kina, teed, canny, normal na ugawaji wa sehemu. Kila ingizo la udhibiti lina swichi yake ya preprocess. `strength` ni 0.05 hadi 1, `num_inference_steps` ni 1 hadi 70, na hadi picha 8 zinaweza kurejeshwa kwa ombi. LoRA na uwakilishi wa vekta vinaweza kutolewa, na tokeo ni jpeg au png.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

Eleza picha unayotaka kuzalisha kwa maelezo mengi iwezekanavyo ili kupata matokeo bora.

controlnet_conditioning_scalesi lazima

Ainanumber

Chaguomsingi0.5

0 – 1

Nguvu ya conditioning inayotumiwa na ControlNet.

image_urlinahitajika image

Ainaurl · image

Picha ya kuanzia uzalishaji, iliyotolewa kupitia URL.

negative_promptsi lazima

Ainastring

Chaguomsingi

Kidokezo hasi kinachobainisha maelezo ya picha yasiyotakiwa. Kinaweza kuondoa rangi, vitu, mandhari au vipengele na sifa ndogo, kama vile masharubu, ukungu au mwonekano wa chini.

image_sizesi lazima

Ainaobject

square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9

Vipimo vya tokeo, vinavyobainishwa kiotomatiki kutoka kwenye picha ya udhibiti wakati hakuna ukubwa uliotolewa.

num_inference_stepssi lazima

Ainainteger

Chaguomsingi35

1 – 70

Idadi ya hatua za inference zitakazoendeshwa.

guidance_scalesi lazima

Ainanumber

Chaguomsingi7.5

0 – 20

Nguvu ya kufuata kidokezo kwa uteuzi wa picha, iliyoonyeshwa kama CFG (Classifier Free Guidance).

strengthsi lazima

Ainanumber

Chaguomsingi0.95

0.05 – 1

Kiwango cha ufanano kati ya picha iliyozalishwa na picha ya awali.

seedsi lazima

Ainainteger | null

Mbegu ya kurudia picha katika Stable Diffusion. Picha inaweza kurudiwa kwa usahihi kila uendeshaji kwa kuweka toleo la modeli, kidokezo na mbegu bila kubadilika.

num_imagessi lazima num_outputs

Ainainteger

Chaguomsingi1

1 – 8

Idadi ya picha iliyoombwa kwa uzalishaji.

lorassi lazima

Ainaobject[]

Chaguomsingi[]

Uzani wa LoRA uliochaguliwa kutumika, uliotolewa kama orodha.

loras[].forcesi lazima

Ainaboolean

Chaguomsingifalse

Ikiwa matumizi ya embedding ni ya lazima: true huifanya kuwa ya lazima.

loras[].pathinahitajika

Ainastring

Chanzo cha uzani wa LoRA, kinachotolewa kama kitambulishi cha modeli ya HF kinachoelekeza kwenye uzani wa safetensors au kama faili ya safetensors inayopatikana kwa URL au njia.

loras[].scalesi lazima

Ainanumber

Chaguomsingi1

0 – 1

Kizidishi kinachotumika kwenye uzito wa LoRA kabla ya kuunganishwa na modeli msingi.

embeddingssi lazima

Ainaobject[]

Chaguomsingi[]

Embeddings zilizochaguliwa kutumika, zilizotolewa kama orodha.

embeddings[].pathinahitajika

Ainastring

Uzani wa embedding uliobainishwa kwa URL au njia ya faili.

embeddings[].tokenssi lazima

Ainastring[]

Orodha ya tokeni za embedding, yenye majina ya kiotomatiki ikiachwa: kila vekta katika faili ya embedding hupokea tokeni kutoka kwenye mfuatano <s0>, <s1>, ... .

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Uanzishaji wa kikagua usalama; true huanzisha ukaguzi.

safety_checker_versionsi lazima

Ainaenum

Chaguomsingiv1

v1v2

Chagua kati ya kikagua usalama maalum cha ViT (`v2`) na kikagua cha CompVis (`v1`, chaguomsingi).

expand_promptsi lazima

Ainaboolean

Chaguomsingifalse

Upanuzi wa kidokezo kwa vidokezo vya ziada, unaowashwa true inapowekwa.

formatsi lazima

Ainaenum

Chaguomsingijpeg

jpegpng

Muundo wa faili wa picha inayotokana.

request_idsi lazima

Ainastring

Chaguomsingi

Kitambulishi cha ombi cha kuhusisha jibu na ombi lililolitengeneza.

preserve_aspect_ratiosi lazima

Ainaboolean

Chaguomsingifalse

Weka true ili kuhifadhi uwiano wa vipengele wa picha inayozalishwa hata ukubwa wake unapozidi kikomo. Ili kupata uwiano sahihi kwa kupunguza baada ya uzalishaji, weka crop_output kuwa True. Thamani za upana au urefu zisizogawanyika kwa 32 bado huzungushwa hadi kizidishi cha 32 kilicho karibu zaidi, na ubadilishaji huu wa ukubwa hauhifadhi uwiano wa vipengele kwa chaguomsingi.

crop_outputsi lazima

Ainaboolean

Chaguomsingifalse

Punguza tokeo lililozalishwa hadi uwiano sahihi wa vipengele wakati true.

openpose_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

openpose_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya openpose.

depth_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

depth_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya depth.

teed_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

teed_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya teed.

canny_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

canny_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya canny.

normal_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

normal_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya normal.

segmentation_image_urlsi lazima

Ainaurl · image

URL inayoelekeza kwenye picha ya udhibiti.

segmentation_preprocesssi lazima

Ainaboolean

Chaguomsingitrue

Hudhibiti uchakataji wa awali wa picha ya segmentation.

inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

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"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

images: array of object {url, width, height, content_type}Maelezo ya faili za picha zilizozalishwa.
timings: object
seed: integerSeed ya uzalishaji wa picha, ikijumuisha thamani iliyochaguliwa bila mpangilio ikiwa ingizo halikutoa seed; vinginevyo, hurudia thamani iliyotolewa.
has_nsfw_concepts: array of booleanHuonyesha ikiwa dhana za NSFW zinaonekana katika picha zilizozalishwa.
prompt: stringKidokezo kinachotumika wakati wa uzalishaji wa picha.

Miundo zaidi: Uhariri wa Picha

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/sdxl-controlnet-union/image-to-image.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu SDXL ControlNet Union · Image to Image

Vigezo

Tokeo

Tofauti nyingine za SDXL ControlNet Union

SDXL ControlNet Union Tofauti: 3

SDXL ControlNet Union · Inpainting Tofauti: 3

Miundo zaidi: Uhariri wa Picha

FLUX.1 Kontext [pro] Tofauti: 7

GPT Image 2.5 Edit Tofauti: 4

Nano Banana 2 Edit Tofauti: 2

Nano Banana Pro Edit Tofauti: 2