Ltx 2.3 Quality · Reference Video to Video
集成
模型 id
ltx-2.3-quality/reference-video-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/ltx-2.3-quality/reference-video-to-video?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",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx-2.3-quality/reference-video-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + 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",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-quality/reference-video-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/zh/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": "ltx-2.3-quality/reference-video-to-video",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
}
通过 Doitong API 调用 Ltx 2.3 Quality · Reference Video to Video 模型(ltx-2.3-quality/reference-video-to-video)。智能体文档:https://doitong.com/zh/developers/models/ltx-2.3-quality/reference-video-to-video.md
POST https://api.doitong.ru/v1/run/ltx-2.3-quality/reference-video-to-video?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",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
如果响应状态为 "queued" 或 "running",请轮询 GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20,直到状态变为 "succeeded";文件位于 outputs[].url。使用相同请求体 POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/reference-video-to-video,可在运行前返回确切价格。
与示例类似的文件: $0.27 270 API 积分 · ≈ ₽29.05 运行前会测量你的文件 在此页面运行
你的新 API 密钥。 它仅在此时显示,并且已填入下方的代码和 API 密钥字段中。请妥善保密:切勿将其放入在浏览器中运行的代码。
构建请求
控件根据模型架构生成。更改控件时,代码和价格会同步更新。
POST
/run/ltx-2.3-quality/reference-video-to-video?wait=20
报价 → $0.27
# 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/ltx-2.3-quality/reference-video-to-video?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",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}'
# 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 $DOITONG_API_KEY"
const API = "https://api.doitong.ru/v1";
const headers = {
"Authorization": "Bearer " + process.env.DOITONG_API_KEY,
"Content-Type": "application/json",
};
// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx-2.3-quality/reference-video-to-video?wait=20", {
method: "POST",
headers,
body: JSON.stringify({
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);
// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + 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",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}
# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-quality/reference-video-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": "ltx-2.3-quality/reference-video-to-video",
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
},
"wait_seconds": 20
}
}
}
关于 Ltx 2.3 Quality · Reference Video to Video
根据必需的 `prompt` 和提供运动与结构的参考 `video_url` 创建新视频。可选的 `image_url`、`mid_image_url` 和 `end_image_url` 用于固定开头、中间和结尾的外观。`video_strength` 和 `strength`(均为 0 至 1)控制对源视频的跟随或保留程度,`control_video_url` 可提供预计算的控制信号。`resolution` 提供 auto 或固定预设,例如方形以及 16:9 竖屏或横屏。
参数
发送规范名称或原生名称之一,不要同时发送两者。 规范名称
名称类型
默认值允许值
描述
prompt必填
类型string
用于引导生成的提示词。
video_url必填
video
类型url · video
指向用于引导运动和结构的参考视频的 URL。
control_video_url可选
类型url · video
可选的预计算控制视频;与 `skip_control_preprocess` 一起提供时,会替代内置控制估计。重新采样以匹配输出尺寸和帧数后,它会成为直接控制信号。例如,该视频可以包含已渲染的深度、边缘或姿态合成结果。
skip_control_preprocess可选
类型boolean
默认值false
使用 `control_video_url` 的直接控制模式,而不是在内部估计深度、边缘或姿态;未提供该 URL 时,此设置会被忽略。此模式下的输出尺寸遵循显式尺寸,并按 64 对齐,以保持 RGB 视频与控制视频匹配;`auto` 则在 LTX 限制内采用源视频尺寸和宽高比。
preserve_original_video可选
类型boolean
默认值false
原始视频保留模式,仅在同时使用 `skip_control_preprocess`、`video_url` 和 `control_video_url` 时可用。默认禁用,不会改变标准控制处理;启用后会从 `video_url` 开始生成,同时保留 `control_video_url` 的结构引导。通过 `strength` 设置去噪程度,即保留量;较低的值会保留更多原始像素。
image_url可选
image
类型url · image
可选的图像锚定样式或角色身份,作为第一帧关键帧。
mid_image_url可选
类型url · image
可选的图像锚定外观,位于片段中点附近,用于补充初始 `image_url` 关键帧。它有助于使外观跟随摄像机运动而不是漂移;需要 `image_url`。
end_image_url可选
end_image
类型url · image
可选的图像锚定外观,位于片段最后一帧。当摄像机运动结束位置不同于起始图像时很有用;需要 `image_url`。
video_strength可选
类型number
默认值0.6
0 – 1
此条件强度控制参考视频中运动和结构的可修改程度:较小的值允许更大的变化。
strength可选
类型number
默认值1
0 – 1
参考视频转视频采样的去噪控制,其效果取决于 `preserve_original_video`。该模式关闭时,它只会缩短去噪调度;开启时,它控制源像素的变换,1.0 会全部重新生成,较低的值会保留更多内容(例如,0.5 大约保留 50%)。
num_frames可选
类型integer
默认值121
9 – 481
输出帧数,受基于分辨率乘以帧数的 IC-LoRA 稳定性预算限制。422 响应表示超出该预算:请降低分辨率或 `num_frames`。该预算允许 720p 级尺寸约 150 帧,较小尺寸允许更多帧。
resolution可选
类型object
默认值auto
autosquare_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
输出视频尺寸,也会影响稳定时长:较小尺寸允许更多帧,较大尺寸会降低最大帧数。内置控制估计会使尺寸接近官方控制流程;通过 `skip_control_preprocess` 和 `control_video_url` 进行直接控制时,则遵循显式尺寸并按 64px 对齐。直接控制模式下,`auto` 在 LTX 限制内继承源视频尺寸和宽高比。
frames_per_second可选
类型number
默认值24
1 – 60
输出视频帧率,以每秒帧数为单位。
num_inference_steps可选
类型integer
默认值15
8 – 30
设置运行的推理步骤数,最多 30;保持不变时使用 15。
guidance_scale可选
类型number
默认值1
1 – 20
使用此比例调整 classifier-free guidance;其默认调校兼顾高质量和快速生成。
generate_audio可选
类型boolean
默认值true
返回 MP4 的音轨开关:关闭时生成仅包含视频的文件,开启时包含音频。
negative_prompt可选
类型string
默认值color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards
指定生成应避免内容的负面提示词。
seed可选
类型integer | null
使生成结果可复现的种子。设置为 None 时会随机选择种子。
enable_prompt_expansion可选
类型boolean
默认值true
控制是否启用提示词扩展。
enable_safety_checker可选
类型boolean
默认值true
控制是否启用安全检查。
video_quality可选
类型enum
默认值high
lowmediumhighmaximum
应用于输出视频的质量预设。
video_write_mode可选
类型enum
默认值balanced
fastbalancedsmall
结果视频的写入模式。
必填
规范名称,也可接受
文件参数接受公开的 https:// URL、最大 10 MB 的 data: URI,或上传文件的 file_url。 文件
输出
GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
"id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
"object": "request",
"model": "ltx-2.3-quality/reference-video-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": 270,
"usd": "0.27",
"charged": 270,
"refunded": 0
},
"input": {
"prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
"video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
},
"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
},
"seed": 42,
"prompt": "string"
},
"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"
}
}
你的文件,由你选择每个 outputs[].url 都是存储中的副本:可永久保存(按 GB-月付费),也可免费保存 7 天,由账户设置或 ?storage= 决定。
每个模型的结构相同图像、视频和音频均包含 type、url、content_type、width、height 和 duration。output 是模型自身的结果对象。
输出字段
- video
- object {url, content_type, file_name, file_size}模型生成的视频。
- seed
- integer生成期间实际使用的种子。
- prompt
- string生成提示词,包括使用前应用的任何扩展内容。
其他 LTX 2.3 Quality 变体
更多模型:视频转换
对于 AI 代理:此页面的 Markdown 版本位于 https://doitong.com/zh/developers/models/ltx-2.3-quality/reference-video-to-video.md. 所有模型和指南: https://doitong.com/developers/llms.txt