Kling Omni Video O3

kwaivgi/kling-video-o3/video-edit

kwaivgi/kling-video-o3/video-edit. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。

相關模型

Kling Omni Video O3 相關模型 1

完整參數參考、輸出結構與即時價格

AI 模型 API 市集一個平台,全部完成最受歡迎服務條款瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
imagesImagesimage_upload—image/* · 1–7 items
promptPrompttextarea—≤ 5000 chars
resolutionGeneration Modeselect720P720P | 1080P
soundSoundbooleanfalse—
keep_original_soundKeep Original Soundbooleantrue—
multi_shotMulti Shotboolean——
shot_typeShot Typeselect—customize | intelligence
multi_promptMulti Promptarray<object>——
↳durationDurationnumber5—
↳promptPrompttext——

完整參數參考、輸出結構與即時價格

深入了解一個平台,全部完成瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
videosarray<string>

API

瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-o3/video-edit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "images": [
      "https://assets-public.namifusion.com/marketplace/images/2026-04-14/54456cddb7de.png"
    ],
    "prompt": "Use reference image 1 as the female character and reference.",
    "resolution": "720P",
    "sound": false,
    "keep_original_sound": false,
    "shot_type": "intelligence"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-o3/video-edit",
    headers=HEADERS,
    json={
        "input": {
            "images": [
                "https://assets-public.namifusion.com/marketplace/images/2026-04-14/54456cddb7de.png"
            ],
            "prompt": "Use reference image 1 as the female character and reference.",
            "resolution": "720P",
            "sound": False,
            "keep_original_sound": False,
            "shot_type": "intelligence"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-o3/video-edit", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "images": [
        "https://assets-public.namifusion.com/marketplace/images/2026-04-14/54456cddb7de.png"
      ],
      "prompt": "Use reference image 1 as the female character and reference.",
      "resolution": "720P",
      "sound": false,
      "keep_original_sound": false,
      "shot_type": "intelligence"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

API 文件

Kling Video O3 Video Edit

Advanced Video Modification via Natural Language

Kling Omni Video O3 Video Edit empowers developers to modify existing videos using natural language instructions. By combining a source video with precise text prompts, the model can alter styles, swap elements, or adjust specific actions while maintaining the original video's structural integrity. Optimized for professional creative pipelines, it offers a cost-effective solution for rapid video iteration and post-production.

🚀 Key Features

  • Instruction-Based Editing: Transform videos by simply describing the changes you want to see.
  • Temporal Consistency: Ensures that edits remain fluid and consistent across the entire duration of the clip.
  • Style & Element Swapping: Change the environment, clothing, or artistic style of a video without manual frame-by-frame editing.
  • Duration Alignment: The edited output length automatically matches the duration of the source video.
  • Fixed Aspect Ratio: Maintains the original aspect ratio of the source video for maximum fidelity.
  • Audio Preservation: Option to keep the original soundtrack while the visual content is being modified.

🛠️ Technical Specifications

ParameterTypeRequiredDefaultRange/OptionsDescription
promptstringYes--Text instructions describing the edits or changes
videostringYes--The source video URL (3–10 seconds)
negative_promptstringNo--Descriptions of elements to avoid in the edit
keep_original_soundbooleanNoTrue-Retain original sound from the source video
shot_typestringNocustomizecustomize, intelligentEditing mode for generation

💰 Pricing

Attribute720P1080P
Video Edit + Silent0.12600.1680
Video Edit + Original Sound0.12600.1680

Billing Rules:

  • All prices are in USD.
  • Billing is based on the duration of the input video.
  • Rates are determined by output resolution and audio status.
  • Supported duration: 3–10 seconds.

💡 Best Use Cases

  • Post-Production: Quickly adjust colors, lighting, or background elements in existing footage.
  • E-commerce & Ads: Update product videos with new seasonal styles or localized text/elements.
  • Social Media Trends: Apply viral artistic styles or filters to personal videos using text prompts.
  • Film & Animation: Iteratively refine character appearances or environmental details during the concept phase.

🔗 Related Models

  • Kling Video O3 Text-to-Video: Generate videos from scratch using text prompts.
  • Kling Video O3 Image-to-Video: Animate static images into dynamic videos.
  • Kling Video O3 Reference-to-Video: Generate videos with high character consistency using reference images.