Kling 3.0 Pro Image to Video
Integriruj
kling-video/v3/pro/image-to-video
# 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/kling-video/v3/pro/image-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/kling-video/v3/pro/image-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": False,
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kling-video/v3/pro/image-to-video", 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/rom/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": "kling-video/v3/pro/image-to-video",
"input": {
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}
}
Kall o Kling 3.0 Pro Image to Video modelo (kling-video/v3/pro/image-to-video) vas o Doitong API. Dokumentacia vaš agentura: https://doitong.com/rom/developers/models/kling-video/v3/pro/image-to-video.md
POST https://api.doitong.ru/v1/run/kling-video/v3/pro/image-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json
{
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}
Te o response status si "queued" vaj "running", ker polling GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 dži kaj te avel "succeeded"; e fajlo si andro outputs[].url. POST https://api.doitong.ru/v1/quote/kling-video/v3/pro/image-to-video sa jekhe body-esa del o precizno molipen angl-o phiripen.
Kava mangipen: $0.56 560 API krediti · ≈ ₽59.68 Phir les kate
Tiro nevo API klidin. Dikhavel pes akana numa thaj si angleder ando kodo thaj ando API klidin kotor tele. Garav les: na thovel les ande kodo savo keren andre jekh browser.
Primerura
Ker jekh mangipen
O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.
/run/kling-video/v3/pro/image-to-video?wait=20
hesab → $0.56
# 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/kling-video/v3/pro/image-to-video?wait=20" \
-H "Authorization: Bearer $DOITONG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/kling-video/v3/pro/image-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
import os
import requests
API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}
payload = {
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": False,
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kling-video/v3/pro/image-to-video", 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": "kling-video/v3/pro/image-to-video",
"input": {
"prompt": "The paper boat drifts forward with the current, raindrops ripple around it, neon reflections shimmer on the wet street, the camera follows at water level.",
"image": "https://content.doitong.com/dev-api/2026/10/21/req_rrqclmu39lveihzpwxufalbn/0-oGMt1xgBCGjIy2tBNDIKy_MSH2rhkY.png",
"duration": 5,
"generate_audio": false
},
"wait_seconds": 20
}
}
}
Phandel kava mangipen
Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ
Kerdo pe Doitong
Publikane khera kerde Kling v3-sa e Doitong komunitetostar. Pheripen jekh prompto ande jekh klik.
Video
Оживи исходное изображение. Полностью сохрани внешность девушки, лицо, причёску, одежду, интерьер, цвета, композицию и русский текст. Девушка смотрит прямо на зрителя, естественно улыбается, моргает, слегка наклоняется вперёд и показывает пальцем на зрителя. Она естественно произносит по-русски:...
Video
Оживи исходное изображение, полностью сохрани внешность девушки и дизайн розового персонажа, их лица, цвета, интерьер, композицию и существующий русский текст. Розовый персонаж оживает, смотрит на зрителя, радостно улыбается, моргает, слегка подпрыгивает и машет рукой. Он произносит по-русски:...
Video
Make A warm, emotional 25 second video cinematic scene of a 4 years of boy with dark brown hair and big eyes having a difficult moment—crying, reaching toward their mother, and showing frustration. The mother initially looks concerned,she listens him then gently kneels down, makes eye contact,...
Video
Ты эксперт в медиа продвижении в социальных сетях --- Название рилс: "Ошибка №1 После Развода: Почему ты тормозишь себя?" Хук (Первые 3-5 секунд): * Визуал: Крупный план вашего лица, выражающего легкое недоумение или задумчивость. Затем резкий переход к черно-белой картинке или затемнению. *...
Video
🎬 Фильм «Мамы больше нет» Общий стиль для всех сцен: Фотореалистичный современный российский художественный фильм. Настоящие люди, реальные человеческие лица, натуральная кожа, естественная мимика и движения. Реальная квартира, естественный дневной и вечерний свет, кинематографическая камера,...
Video
Use the uploaded image as the exact identity and appearance reference. Create a short hyperrealistic video where the woman keeps exactly the same face, identity, facial features, proportions, skin tone, hairstyle, bouquet, white shirt, pink balloons, candles “24”, and background. The motion must...
Video
Медленное плавное приближение камеры к гигантскому флакону духов в миниатюрном ночном городе. Две маленькие машины спокойно проезжают по дороге перед основанием флакона. Вдали едва заметно движется лёгкая дымка. Огни города мягко отражаются на мокром асфальте. Флакон стоит неподвижно. Его форма,...
Video
Девушка всилит дома смотрит интернете ищет салон красоты ,находит салон,приходит в салон наш с кудрявыми волосами ,другой мастер кератиновое выпрямление волос ,и она смотрит на свои волосы в зеркало и очень счастлива и благодарит мастера Анастасию Render entirely in "Claymation" style — match its...
Video
Animate this baby very gently and naturally. She is lying on her tummy and happily playing with the colorful toy in front of her. She smiles warmly, softly blinks, makes tiny hand and finger movements toward the toy, slightly wiggles her body, and shows subtle natural breathing. The toy can move...
Video
The toddler slowly lowers his raised hand and gently pats his own bottom, then continues rhythmically patting his bottom many times, slowly and softly, his palm touches only his own body, his hand stays close to his body, like a mother soothing a baby, in a sweet cute baby voice he quietly coos...
Video
Дверь кофейни резко открывается. Внутрь заходит эффектная рыжеволосая девушка в чёрной кожаной куртке, шлем под мышкой. На улице у входа виден её мощный мотоцикл. Она уверенно подходит к стойке. Бариста — симпатичный парень-ботан в очках, с растрёпанными волосами, — поднимает глаза от кофемашины....
Video
A cinematic 3D Pixar-style animation. The same young firefighter gently polishes his silver helmet marked with the number 5. He blinks naturally, smiles slightly, and turns his eyes toward the flashing red alarm light. Red emergency lights pulse and reflect on his helmet and face. Subtle hand...
Video
Cinematic 3D Pixar-style animation. The same young firefighter from the previous shot suddenly hears the emergency alarm. His expression changes from calm to determined. He quickly turns his head toward the flashing red alarm light, grabs his silver firefighter helmet marked with the number 5,...
Video
Ultra-realistic 4K ASMR video, vertical 9:16. A whole fresh brown coconut with a realistic hairy shell sits on a beautiful dark wooden cutting board. Cinematic macro close-up, soft studio lighting, luxurious satisfying aesthetic. A hand slowly approaches holding a sharp stainless steel knife. The...
Video
VISUAL CORRECTION. This replaces the previous request entirely. Subject: a compact studio room A reference supplies identity ONLY. Keep the recognizable subject and visual style, but implement the requested changes to size, parts, pose, setting and composition. The actual result MUST visibly...
Video
VISUAL CORRECTION. This replaces the previous request entirely. Subject: why leaves have veins A reference supplies identity ONLY. Keep the recognizable subject and visual style, but implement the requested changes to size, parts, pose, setting and composition. The actual result MUST visibly...
Palal Kling 3.0 Pro Image to Video
Klingeskero flagship image-to-video modelo stabilno arakhel e start kipeskero subjekto, thaj dodavel naturalno motijane, kamera-motijane thaj, standardno, jekhutne šume thaj vakeripe. De les jekh agorutno kipo te kontrolisarel kaj o shot agorisarel, divisarel jekh keripe ande but shotura e shotoskere promptonca, vaj pinisararel pale-avde karakterija thaj predmetura e referencne elementonca. O kadroskero obliko lel pes katar o start kipo.
Parametra
Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava
promptopcionalno
multi_promptopcionalno
multi_prompt[].prompttrubul
multi_prompt[].durationopcionalno
start_image_urltrubul
image
durationopcionalno
generate_audioopcionalno
end_image_urlopcionalno
end_image
elementsopcionalno
elements[].frontal_image_urlopcionalno
elements[].reference_image_urlsopcionalno
elements[].video_urlopcionalno
elements[].voice_idopcionalno
shot_typeopcionalno
negative_promptopcionalno
cfg_scaleopcionalno
Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura
Rezultato
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "kling-video/v3/pro/image-to-video",
"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": 560,
"usd": "0.56",
"charged": 560,
"refunded": 0
},
"input": {
"prompt": "The banana manager turns to the camera, smiles and waves while coworkers keep typing, gentle handheld camera",
"image": "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png",
"duration": 5
},
"output": {
"video": {
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
"content_type": "video/mp4",
"file_name": "0-output.mp4",
"file_size": 1843200
}
},
"outputs": [
{
"type": "video",
"url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
"content_type": "video/mp4",
"file_size": 1843200,
"width": 1280,
"height": 720,
"duration": 5,
"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"
}
}
Outputoske fieldura
- video
- object {url, content_type, file_name, file_size}Video kerdo modelostar.
Aver variantura e Kling v3
Bute modeli: Kip ko Video
AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/kling-video/v3/pro/image-to-video.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt