Kling O3 4K - Reference to Video

Try Kling O3 4K - Reference to Video in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: kling-video-o3-4k-reference-to-video Part of the Kling 3.0/o3 family on fal.ai, this 4K reference-to-video model generates native 4K (3840x2160) video from reference images and text prompts with no upscaling step. It excels at preserving identity, layout, and stylistic detail while adding cinematic motion, camera movement, and scene progression. Supports element and style references (combined limit of 7), optional start and end frame anchoring, multi-shot generation up to 15 seconds, and optional native synchronized audio in English and Chinese. Optimized for advertising, branded content, and production-grade scene work where 4K detail is required.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Sync
Async
Async with SSE

This blocks until the video is ready (typically 5-15 minutes). Prefer Async or Async with SSE for anything beyond quick experimentation.See the video generation reference for more details.

Minimal
Basic parameters
All parameters

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video"
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "kling-video-o3-4k-reference-to-video"
    },
)
response.raise_for_status()
print(response.json())

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ]
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ]
    },
)
response.raise_for_status()
print(response.json())

curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "aspect_ratio": "16:9",
  "generate_audio": false
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/videos/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "aspect_ratio": "16:9",
        "generate_audio": false
    },
)
response.raise_for_status()
print(response.json())

See the async queue reference for more details.

Minimal
Basic parameters
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video"
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "kling-video-o3-4k-reference-to-video"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ]
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ]
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "aspect_ratio": "16:9",
  "generate_audio": false
}' | jq -r '.generations[0].generation_id')

# Poll until the generation reaches a terminal status.
while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  echo "Status: $STATUS"
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 5
done

# Print the result.
curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "aspect_ratio": "16:9",
        "generate_audio": false
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(5)

if data["status"] == "succeeded":
    print(f"Result: {data['result_url']}")
else:
    print(f"Generation {data['status']}: {data.get('error_message')}")

See the async queue reference for more details.

Minimal
Basic parameters
All parameters

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "kling-video-o3-4k-reference-to-video"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ]
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ]
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "kling-video-o3-4k-reference-to-video",
  "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input_image": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "aspect_ratio": "16:9",
  "generate_audio": false
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "kling-video-o3-4k-reference-to-video",
        "start_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "tail_image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "input_image": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "aspect_ratio": "16:9",
        "generate_audio": false
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/kling-video-o3-4k-reference-to-video

Request parameters

Optional parameters

Field	Type	Default	Description
`start_image_url`	`string`	—	The first frame of the video. The model will try to extend the contents of this frame. Format: uri.
`tail_image_url`	`string`	—	The last frame of the video. Requires start frame to be configured. The model will try to fill in between the frames. Format: uri.
`input_image`	`array<string>`	—	Reference images for style/appearance. Use @Image1, @Image2, etc. in the prompt to refer to them. Maximum 4 total (elements + reference images) when using video.
`elements`	`array<object>`	—	Optional element references. Use @Element1, @Element2, etc. in the prompt to refer to them.
`negative_prompt`	`string`	—	Text describing what to avoid in the generated video.
`aspect_ratio`	`string`	`"16:9"`	Video aspect ratio One of: 9:16, 1:1, 16:9.
`generate_audio`	`boolean`	`false`	Whether to generate native audio for the video. Supports Chinese and English voice output.

Try Kling O3 4K - Reference to Video in the Workbench

​Example request

​Fetch model details

​Request parameters

​Optional parameters

Example request

Fetch model details

Request parameters

Optional parameters