opendunes
Video
Copy page ▾

Reference pictures

Make a clip that keeps the look of pictures you give, without fixing any one frame.

  1. Pick a model that takes them.
  2. Say what must stay the same.
  3. Send the job with the pictures in input_references.
  4. Wait and fetch the clip.

1. Pick a model that takes them

No field of the video models list says whether a model takes reference pictures. Its description does, and on one model its price. On 2026-09-29, these models named them.

LabModelsThe list says
Alibabaalibaba/wan-3.0reference-guided video generation
Alibabaalibaba/wan-2.7multiple reference images guide the style and content
Alibabaalibaba/happyhorse-1.0, alibaba/happyhorse-1.1a set of reference images
ByteDancebytedance/seedance-2.0, -2.0-fast, -2.0-minimultimodal reference-to-video
ByteDancebytedance/seedance-2.5multimodal reference-based generation
xAIx-ai/grok-imagine-videoreference-conditioned
MiniMaxminimax/hailuo-2.3reference images as input
MiniMaxminimax/hailuo-3its pricing_skus holds reference_images

Read a model's description on its page in Models before you build on it. The other fields that narrow the choice: Choose a video model.

2. Say what must stay the same

The pictures show the model what to keep. The prompt says what to keep, and what to change around it.

Prompt partExample
What the pictures holdthe mark from the reference picture
What must not changeits shape and its orange gradient
The new scenecarved in a clay tile on a potter's bench in Maatkas
Camera and lightslow orbit, soft window light

3. Send the job

The sample sends the OpenDunes mark as the one reference picture, to bytedance/seedance-2.0-fast, for 5 seconds at 720p in 1:1. Up to the model, more pictures of the same thing, from other angles, hold it steadier.

import json
import os
import urllib.request

API_KEY = os.environ["OPENDUNES_API_KEY"]
ADDRESS = "https://opendunes.com/v1/videos"
MODEL = "bytedance/seedance-2.0-fast"
REFERENCE = "https://opendunes.com/icon.png"
PROMPT = (
    "The mark from the reference picture, carved in a clay tile on a "
    "potter's bench in Maatkas, slow orbit, soft window light. Keep the "
    "mark's shape and its orange gradient."
)

request = urllib.request.Request(
    ADDRESS,
    data=json.dumps(
        {
            "model": MODEL,
            "prompt": PROMPT,
            "duration": 5,
            "resolution": "720p",
            "aspect_ratio": "1:1",
            "input_references": [
                {"type": "image_url", "image_url": {"url": REFERENCE}},
            ],
        }
    ).encode(),
    headers={
        "Authorization": "Bearer " + API_KEY,
        "Content-Type": "application/json",
    },
)
with urllib.request.urlopen(request) as response:
    job = json.load(response)

print(job["id"], job["status"])
In each input_references entryHolds
typeimage_url
image_url.urlthe picture's address: public HTTPS, answering with the picture itself
Watch out

A picture behind a login, a cookie or a web page is not a picture the provider can read. Test the address in a private browser window: it must show the picture alone.

The answer is 202, with the job's id and status pending. Every field: Clips.

Good to know

References guide the look; they fix no frame. To make a picture the clip's exact first or last frame, send it in frame_images: Picture to video. When both are sent, frame_images wins.

4. Wait and fetch the clip

The job runs as any other: ask GET /v1/videos/{id} every ten seconds until it ends, then fetch the clip from /v1/videos/{id}/content?index=0, or give a callback_url and have the end posted to you. The whole loop, in four languages: Text to video. The post: Video webhooks.

The clip is charged in DADAThe Algerian dinar, the one currency the docs show.More on Balance and charges → once, when the job reports completed. On some models each picture sent in is charged too: the model's page in Models lists what it charges for, and Choose a video model names the models. A job that ends any other way charges nothing.

Last modified on