Skip to content

Bernini-R Reference to Video

Integrate

Model id bernini-r/reference-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/bernini-r/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Files like the example: $0.405 405 API credits your files are measured before the run Run it on this page

Get API key
Open model Reference to Video Reference inputs #video#stylized

Generates one continuous video from one to five reference subject images and a prompt

Open model · Video

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required

Text describing the prompt or requested edit.

•required reference_image_urls
Drop a file, or · up to 5

Images providing subject references, with a maximum of 5.

aspect_ratio default 16:9

Aspect ratio for the output.

default 848

Longer-edge pixel setting: editing uses it as a size ceiling for source/reference media, while generation uses it to set output size.

default 81

Frame count, adjusted internally to the form 4k+1.

default 16

Frame rate of the output, in frames per second.

Advanced negative_prompt · acceleration · num_inference_steps · seed · enable_prompt_expansion · enable_safety_checker

Negative prompt, using Wan2.2's standard negative prompt when unspecified.

acceleration default none

Degree of acceleration to apply.

default 30

Count of denoising steps to perform.

Seed that enables reproducible results; chosen randomly if omitted.

POST /run/bernini-r/reference-to-video?wait=20 quote → $0.405
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/bernini-r/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Bernini-R Reference to Video

Give a `prompt` and between one and five `reference_image_urls`; the model builds a single video featuring those subjects. `aspect_ratio` can be 16:9, 9:16 or 1:1. You can tune `num_frames` (5 to 121), `frames_per_second` (4 to 30) and `num_inference_steps` (1 to 50). A `negative_prompt` and prompt expansion are optional.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
promptrequired
Typestring
Text describing the prompt or requested edit.
negative_promptoptional
Typestring | null
Negative prompt, using Wan2.2's standard negative prompt when unspecified.
num_inference_stepsoptional
Typeinteger
Default30
1 – 50
Count of denoising steps to perform.
max_image_sizeoptional
Typeinteger
Default848
256 – 1,280
Longer-edge pixel setting: editing uses it as a size ceiling for source/reference media, while generation uses it to set output size.
seedoptional
Typeinteger | null
Seed that enables reproducible results; chosen randomly if omitted.
enable_prompt_expansionoptional
Typeboolean
Defaultfalse
Optional pre-generation prompt rewriting by an LLM, disabled by default despite the model being tuned on enhanced prompts.
num_framesoptional
Typeinteger
Default81
5 – 121
Frame count, adjusted internally to the form 4k+1.
frames_per_secondoptional
Typeinteger
Default16
4 – 30
Frame rate of the output, in frames per second.
accelerationoptional
Typeenum
Defaultnone
noneregular
Degree of acceleration to apply.
reference_image_urlsrequired images
Typeurl[] · image
≤ 5 items
Images providing subject references, with a maximum of 5.
aspect_ratiooptional
Typeenum
Default16:9
16:99:161:1
Aspect ratio for the output.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "bernini-r/reference-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 405,
    "usd": "0.405",
    "charged": 405,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "reference_image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42,
    "actual_prompt": "string"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
video
object {url, content_type, file_name, file_size}Video resulting from generation or editing.
seed
integerSeed applied during generation.
actual_prompt
string | nullFinal expanded prompt, populated only if prompt expansion was performed.

More models: Reference to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/bernini-r/reference-to-video.md. All models and guides: https://doitong.com/developers/llms.txt