Kling Omni Video O1 Reference-to-Video

kwaivgi/kling-video-o1/reference-to-video

Kling Omni Video O1 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Examples

Kling Omni Video O1 Reference-to-Video example 1

Parameters

NameTypeDefaultConstraintsDescription
promptPrompttextarea≤ 5000 charsDescribe the scenario for the new video content. Be specific about actions, camera movements, and atmosphere.
imagesReference Imagesimage_uploadimage/* · 0–7 itemsUpload up to 7 reference images (character, prop, or scene). If a reference video is used, the limit is reduced to 4 images.
resolutionGeneration Modeselect720P720P | 1080P
aspect_ratioAspect Ratioselect16:916:9 | 9:16 | 1:1Select the aspect ratio of the generated video.
durationDurationselect53 | 4 | 5 | 6 | 7 | 8 | 9 | 10The duration of the generated media in seconds (3-10).
keep_original_soundKeep Original SoundbooleantrueSelect whether to keep the video original sound when a reference video is provided.
video_listVideo Listarray<object>Reference Video list. Supports base video for editing or feature reference.
video_url *Video URLtextThe URL of the reference video (MP4/MOV, 720p-2160p, max 200MB).
refer_typeReference Typeselectbasebase | featureType of reference: 'base' for editing/transformation, 'feature' for style/content reference.
keep_original_soundKeep Original Soundselectyes | noWhether to keep the original sound of the video.

API

Call this model through one unified REST API. Get a key on the API Keys page.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-video-o1/reference-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "Use reference image 1 as the female character and reference.",
    "images": [
      "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/marketplace/thumbnails/2026-02-06/3233ef941e4e.png"
    ],
    "resolution": "720P",
    "aspect_ratio": "16:9",
    "duration": 5,
    "keep_original_sound": false
  }
}'

# 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-o1/reference-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "Use reference image 1 as the female character and reference.",
            "images": [
                "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/marketplace/thumbnails/2026-02-06/3233ef941e4e.png"
            ],
            "resolution": "720P",
            "aspect_ratio": "16:9",
            "duration": 5,
            "keep_original_sound": False
        }
    },
)
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 600s server-side.
deadline = time.time() + 660
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-o1/reference-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "Use reference image 1 as the female character and reference.",
      "images": [
        "https://kaito-1328216764.cos.ap-tokyo.myqcloud.com/marketplace/thumbnails/2026-02-06/3233ef941e4e.png"
      ],
      "resolution": "720P",
      "aspect_ratio": "16:9",
      "duration": 5,
      "keep_original_sound": false
    }
  }),
});
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 600s server-side.
const deadline = Date.now() + 660 * 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);

Documentation

Kling Omni Video O1

Effortless Reference-to-Video Generation with Identity Consistency

Kling Omni Video O1 is a cutting-edge image-to-video AI model designed to generate creative videos using character, prop, or scene references from multiple viewpoints. By extracting subject features, it ensures identity consistency across frames while creating entirely new video content. With no cold starts, affordable pricing, and seamless REST API integration, this model offers unmatched performance for developers and creators.

🚀 Key Features

  • Identity Lock: Maintains subject features consistently across all frames, including facial expressions, clothing, and props.
  • Multi-Angle Support: Accepts references from various viewpoints to enhance subject accuracy.
  • Scene Flexibility: Places subjects in new environments and scenarios while retaining their core identity.
  • Motion Control: Allows users to guide subject actions and camera movements using text prompts.
  • Creative Freedom: Generates entirely new poses, actions, and scenes, enabling diverse creative possibilities.

🛠️ Technical Specifications

ParameterTypeDefault ValueOptions/RangeDescription
PromptString--Positive prompt for video generation.
VideoString--URL of the reference video.
ImagesArray-≤4 (with video), ≤7 (without video)Reference images for subject creation.
Keep Original SoundBooleanTrueTrue/FalseRetain original audio from reference video.
Aspect RatioString16:916:9, 9:16, 1:1Aspect ratio of the generated video.
DurationInteger53–10 secondsLength of the generated video.

💰 Pricing

Attribute720P1080P
No Reference Video0.08400.1120
With Reference Video0.12600.1680

Billing Rules:

  • Total Cost = Price per second × Duration (3-15 seconds).

💡 Best Use Cases

  • E-commerce: Showcase products with dynamic videos featuring consistent branding elements.
  • Social Media: Create engaging content with unique scenarios and camera movements.
  • Film Production: Generate character animations or scene previews for pre-production workflows.
  • Advertising: Develop creative commercials with consistent subject representation.

🔗 Related Models

  • Kling Omni Video Pro: Enhanced version with advanced motion control and higher resolution support.
  • Kling Omni Video Ultra: Offers ultra-wide aspect ratio and extended duration capabilities.

Related models

VT Lip Sync
Video to VideoNamiFusion

VT Lip Sync

VT Lip Sync synchronizes mouth movements for a translated video by using the translated target video, translated audio, translated subtitle timing, and the original source video with its original subtitle timing.

from $0.200 / per run
Kling Omni Video O3
Video to VideoKling

Kling Omni Video O3

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

from $0.380 / per run
Kling Omni Video O3
Video to VideoKling

Kling Omni Video O3

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

from $0.630 / per run
Kling Omni Video O1 Reference-to-Video
Video to VideoKling

Kling Omni Video O1 Reference-to-Video

Kling Omni Video O1 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

from $0.380 / per run
Kling 3.0 Standard
Video to VideoKling

Kling 3.0 Standard

Kling 3.0 Standard Motion Control transfers motion from reference videos to animate still images. Upload a character image and a motion clip (dance, action, gesture), and the model extracts the movement to generate smooth, realistic video. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

from $0.380 / per run
seedance-2-0 reference-to-video
Video to VideoDoubao

seedance-2-0 reference-to-video

The "Reference-to-Video" feature of Seedance 2.0 is the ultimate solution for visual stylistic unity. It precisely extracts artistic styles, lighting tones, or compositional intents from reference materials and seamlessly integrates them into newly generated videos, ensuring a highly consistent visual language for your creative series.

from $0.470 / per run
Alibaba WAN 2.6
Video to VideoAlibaba

Alibaba WAN 2.6

Alibaba WAN 2.6 Reference-to-Video seamlessly transforms character, prop, or scene references—supporting both single and multi-view inputs—into high-quality video sequences. It excels at preserving identity, style, and layout while delivering fluid, coherent motion. Experience peak performance via our production-ready REST API, featuring zero cold starts and cost-effective pricing.

from $0.750 / per run