> ## Documentation Index > Fetch the complete documentation index at: https://docs.token-nova.com/llms.txt > Use this file to discover all available pages before exploring further. # omni-fast-v2v 参考视频生成 > 使用 `POST /v1/videos` 调用 `omni-fast-v2v` 做参考视频编辑、延长或重生成。 # omni-fast-v2v `omni-fast-v2v` 使用 JSON 请求体提交异步视频任务，适合把已有 MP4 作为参考视频进行编辑、延长或重生成。 * 异步处理模式，提交后返回 `id` 或 `task_id`。 * 参考视频字段支持 `video`、`video_url` 和 `input_video`。 * 参考视频支持公网 MP4 URL 或 `data:video/mp4;base64,...`。 * 参考视频最大 15MB。 * 不需要参考视频时，优先使用 `omni-fast`。 ## 方法与路径 ```http theme={null} POST /v1/videos ``` ## 请求示例 ```bash cURL theme={null} curl -X POST https://www.token-nova.com/v1/videos \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "omni-fast-v2v", "prompt": "Edit the attached video into a visibly new version while preserving the original camera path, timing, subject motion, and shot continuity. Add a rainy cinematic night look with neon reflections. Output a newly generated video, not the uploaded source clip or its preview.", "video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" }' ``` ```bash video_url 别名 cURL theme={null} curl -X POST https://www.token-nova.com/v1/videos \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "omni-fast-v2v", "prompt": "Extend this clip into a new cinematic shot with the same camera path.", "video_url": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" }' ``` ```bash input_video 别名 cURL theme={null} curl -X POST https://www.token-nova.com/v1/videos \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "omni-fast-v2v", "prompt": "Regenerate the attached clip with brighter lighting and smoother motion.", "input_video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" }' ``` ```python Python theme={null} import requests resp = requests.post( "https://www.token-nova.com/v1/videos", headers={ "Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json", }, json={ "model": "omni-fast-v2v", "prompt": "Edit the attached video into a visibly new version while preserving the original camera path. Output a newly generated video, not the uploaded source clip.", "video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p", }, timeout=120, ) print(resp.json()) ``` ```javascript JavaScript theme={null} const response = await fetch("https://www.token-nova.com/v1/videos", { method: "POST", headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json", }, body: JSON.stringify({ model: "omni-fast-v2v", prompt: "Edit the attached video into a visibly new version while preserving the original camera path. Output a newly generated video, not the uploaded source clip.", video: "https://example.com/source.mp4", seconds: "8", aspect_ratio: "16:9", resolution: "720p", }), }); console.log(await response.json()); ``` ```go Go theme={null} package main import ( "bytes" "encoding/json" "fmt" "io" "net/http" ) func main() { payload := map[string]any{ "model": "omni-fast-v2v", "prompt": "Edit the attached video into a visibly new version while preserving the original camera path. Output a newly generated video, not the uploaded source clip.", "video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p", } body, _ := json.Marshal(payload) req, _ := http.NewRequest("POST", "https://www.token-nova.com/v1/videos", bytes.NewReader(body)) req.Header.Set("Authorization", "Bearer YOUR_API_KEY") req.Header.Set("Content-Type", "application/json") resp, err := http.DefaultClient.Do(req) if err != nil { panic(err) } defer resp.Body.Close() respBody, _ := io.ReadAll(resp.Body) fmt.Println(string(respBody)) } ``` ```java Java theme={null} import java.net.URI; import java.net.http.HttpClient; import java.net.http.HttpRequest; import java.net.http.HttpResponse; public class Main { public static void main(String[] args) throws Exception { String json = """ { "model": "omni-fast-v2v", "prompt": "Edit the attached video into a visibly new version while preserving the original camera path. Output a newly generated video, not the uploaded source clip.", "video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" } """; HttpRequest request = HttpRequest.newBuilder() .uri(URI.create("https://www.token-nova.com/v1/videos")) .header("Authorization", "Bearer YOUR_API_KEY") .header("Content-Type", "application/json") .POST(HttpRequest.BodyPublishers.ofString(json)) .build(); HttpResponse response = HttpClient.newHttpClient() .send(request, HttpResponse.BodyHandlers.ofString()); System.out.println(response.body()); } } ``` ```php PHP theme={null} 'omni-fast-v2v', 'prompt' => 'Edit the attached video into a visibly new version while preserving the original camera path. Output a newly generated video, not the uploaded source clip.', 'video' => 'https://example.com/source.mp4', 'seconds' => '8', 'aspect_ratio' => '16:9', 'resolution' => '720p', ]; $ch = curl_init('https://www.token-nova.com/v1/videos'); curl_setopt_array($ch, [ CURLOPT_POST => true, CURLOPT_HTTPHEADER => [ 'Authorization: Bearer YOUR_API_KEY', 'Content-Type: application/json', ], CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_UNICODE), CURLOPT_RETURNTRANSFER => true, ]); $response = curl_exec($ch); curl_close($ch); echo $response; ``` ## 响应示例 ```json 200 - 提交成功 theme={null} { "id": "video_abc123", "task_id": "video_abc123", "object": "video", "model": "omni-fast-v2v", "status": "queued", "progress": 0, "created_at": 1735689600, "video_url": "" } ``` ```json 200 - 任务查询成功 theme={null} { "id": "video_abc123", "task_id": "video_abc123", "object": "video", "model": "omni-fast-v2v", "status": "completed", "progress": 100, "created_at": 1735689600, "completed_at": 1735689900, "video_url": "https://example.com/results/omni-fast-v2v.mp4" } ``` ```json 200 - 任务失败 theme={null} { "id": "video_abc123", "task_id": "video_abc123", "object": "video", "model": "omni-fast-v2v", "status": "failed", "progress": 100, "error": { "message": "upstream task failed", "code": "task_failed" } } ``` ```json 400 - 参数错误 theme={null} { "error": { "message": "video is required for V2V generation", "type": "invalid_request_error", "param": "video", "code": "invalid_request_error" } } ``` ```json 401 - 认证失败 theme={null} { "error": { "message": "invalid token", "type": "invalid_request_error", "code": "invalid_api_key" } } ``` ```json 402 - 额度不足 theme={null} { "error": { "message": "insufficient quota", "type": "insufficient_quota", "code": "insufficient_quota" } } ``` ```json 413 - 请求体过大 theme={null} { "error": { "message": "request body too large", "type": "invalid_request_error", "code": "request_body_too_large" } } ``` ```json 429 - 请求过多 theme={null} { "error": { "message": "rate limit exceeded", "type": "rate_limit_error", "code": "rate_limit_exceeded" } } ``` ```json 500 - 服务端错误 theme={null} { "error": { "message": "internal server error", "type": "server_error", "code": "server_error" } } ``` ## 认证 使用 Bearer Token 鉴权： ```http theme={null} Authorization: Bearer YOUR_API_KEY ``` 所有请求示例都需要携带 `Authorization` Header。JSON 请求还需要携带： ```http theme={null} Content-Type: application/json ``` ## Body 固定传 `omni-fast-v2v`。示例：`"omni-fast-v2v"`。 视频编辑或生成提示词。建议说明保留哪些运动、镜头或主体，并明确要求输出新视频。示例：`"Edit the attached video into a visibly new version"`。 参考视频。支持公网 MP4 URL 或 `data:video/mp4;base64,...`。与 `video_url`、`input_video` 任选其一。示例：`"https://example.com/source.mp4"`。 `video` 的兼容字段。未传 `video` 时可使用。示例：`"https://example.com/source.mp4"`。 `video` 的兼容字段。未传 `video` 和 `video_url` 时可使用。示例：`"https://example.com/source.mp4"`。 输出时长。建议传字符串；推荐范围为 `4` 到 `30` 秒。示例：`"8"`。 画面比例。示例值：`"16:9"`、`"9:16"`。 分辨率字段。示例值：`"720p"`、`"1080p"`、`"2k"`、`"4k"`。 兼容 `omni-fast` 的首帧图字段。没有参考视频时，建议直接使用 `omni-fast`。示例：`"https://example.com/first-frame.jpg"`。 兼容 `omni-fast` 的多参考图字段，最多 5 张。没有参考视频时，建议直接使用 `omni-fast`。 ## Response 视频任务 ID。后续可用于 `GET /v1/videos/{task_id}` 查询。 视频任务 ID 的兼容字段。通常与 `id` 相同。 对象类型，通常为 `video`。 本次任务使用的模型，例如 `omni-fast-v2v`。 任务状态。常见值为 `queued`、`in_progress`、`completed`、`failed`。 任务进度，常见范围为 `0` 到 `100`。 完成后的视频地址。 任务失败或接口错误时返回的错误对象，通常包含 `message` 和 `code`。 ## 使用场景 ### 公网 MP4 参考视频 ```json theme={null} { "model": "omni-fast-v2v", "prompt": "Extend this clip into a new cinematic shot with the same camera path.", "video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" } ``` ### 本地 MP4 转 data URI ```python theme={null} import base64 from pathlib import Path source = Path("source.mp4") if source.stat().st_size > 15 * 1024 * 1024: raise ValueError("参考视频最大 15MB") video = "data:video/mp4;base64," + base64.b64encode(source.read_bytes()).decode("ascii") ``` ### 使用 `input_video` 别名 ```json theme={null} { "model": "omni-fast-v2v", "prompt": "Regenerate the attached clip with brighter lighting and smoother motion.", "input_video": "https://example.com/source.mp4", "seconds": "8", "aspect_ratio": "16:9", "resolution": "720p" } ``` ## 注意事项 * `omni-fast` 不支持参考视频；V2V 必须使用 `omni-fast-v2v`。 * 参考视频最大 15MB，过大时建议先压缩或转为公网 URL。 * `video`、`video_url`、`input_video` 是同一类参考视频输入，推荐优先使用 `video`。 * 对于 `data:video/mp4;base64,...`，实际请求体会变大，请预留网络超时时间。 * 完成后从返回的 `video_url` 获取生成的 MP4。 ## 相关接口 * [omni-fast](./omni-fast) * [Omni 视频模型概览](./overview) * [OpenAI 视频兼容接口](/zh/videos/openai-videos) * [任务状态接口](/zh/tasks/task-status)