WAN 2.7 - Reference to Video

Try WAN 2.7 - Reference to Video in the Workbench

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

Model ID: wan-v2-7-reference-to-video WAN 2.7 reference-to-video generates video from one or more reference images and reference videos with optional first-frame joint control, supporting single-character performances, multi-character interactions, and multi-shot narration. Up to 5 reference images and reference videos combined; reference identifiers in the prompt (@Image1, @Image2, @Video1, …) match the order of assets within each type. Output up to 1080P at 2-15s (2-10s when a reference video is included).

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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>"
}'

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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>"
    },
)
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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "aspect_ratio": "16:9",
  "resolution": "1080P",
  "duration": 5,
  "prompt_extend": true,
  "watermark": 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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "aspect_ratio": "16:9",
        "resolution": "1080P",
        "duration": 5,
        "prompt_extend": true,
        "watermark": 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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>"
}' | 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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>"
    },
)
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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "aspect_ratio": "16:9",
  "resolution": "1080P",
  "duration": 5,
  "prompt_extend": true,
  "watermark": 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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "aspect_ratio": "16:9",
        "resolution": "1080P",
        "duration": 5,
        "prompt_extend": true,
        "watermark": 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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>"
}' | 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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>"
    },
)
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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "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": "wan-v2-7-reference-to-video",
  "prompt": "<prompt>",
  "reference_images": [
    "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
  ],
  "reference_videos": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
  ],
  "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "aspect_ratio": "16:9",
  "resolution": "1080P",
  "duration": 5,
  "prompt_extend": true,
  "watermark": 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": "wan-v2-7-reference-to-video",
        "prompt": "<prompt>",
        "reference_images": [
            "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png"
        ],
        "reference_videos": [
            "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
        ],
        "input_image": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
        "aspect_ratio": "16:9",
        "resolution": "1080P",
        "duration": 5,
        "prompt_extend": true,
        "watermark": 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/wan-v2-7-reference-to-video

Request parameters

Required parameters

Field	Type	Default	Description
`prompt`	`string`	—	Text prompt describing the desired video. Supports Chinese and English. Max 5000 characters. Use @Image1, @Image2, … to reference the reference images in order, and @Video1, @Video2, … to reference the reference videos in order; identifiers are independent across types.

Optional parameters

Field	Type	Default	Description
`reference_images`	`array<object>`	—	Array of reference images for character/object/scene appearance. Each item has a URL and an optional reference voice. Order maps to @Image1, @Image2, etc. Reference images + reference videos must total ≤ 5. JPEG/JPG/PNG/BMP/WEBP, 240-8000 px per side, aspect ratio 1:8 to 8:1, max 20 MB each.
`reference_videos`	`array<object>`	—	Array of reference videos for character/object appearance, motion, and voice. Each item has a URL and an optional reference voice. Order maps to @Video1, @Video2, etc. Reference images + reference videos must total ≤ 5. MP4/MOV, 1-30s, 240-4096 px per side, aspect ratio 1:8 to 8:1, max 100 MB each.
`input_image`	`string`	—	Optional first-frame image used for joint control. Provides a starting frame the video is generated from. JPEG/JPG/PNG/BMP/WEBP, 240-8000 px per side, max 20 MB. When provided, the output aspect ratio is taken from this image and the aspect_ratio parameter is ignored. Format: uri.
`aspect_ratio`	`string`	`"16:9"`	Aspect ratio of the generated video. Ignored when a first frame image is provided (the model uses the input asset’s ratio). One of: 16:9, 9:16, 1:1, 4:3, 3:4.
`resolution`	`string`	`"1080P"`	Output video resolution tier. One of: 720P, 1080P.
`duration`	`integer`	`5`	Output video duration in seconds. 2-15 with reference images only; 2-10 when any reference video is included. Range: 2 – 15.
`negative_prompt`	`string`	—	Content to avoid in the video. Supports Chinese and English. Max 500 characters.
`prompt_extend`	`boolean`	`true`	Whether the model rewrites short prompts to improve quality. Adds processing time.
`watermark`	`boolean`	`false`	Adds an ‘AI Generated’ watermark to the bottom-right corner.
`seed`	`integer`	—	Random seed for reproducibility (0-2147483647). Range: 0 – 2147483647.

Try WAN 2.7 - Reference to Video in the Workbench

​Example request

​Fetch model details

​Request parameters

​Required parameters

​Optional parameters

Example request

Fetch model details

Request parameters

Required parameters

Optional parameters