Skip to content

Wan · v2.2 A14b · Video to Video

Integrate

Model id wan/v2.2-a14b/video-to-video
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/wan/v2.2-a14b/video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

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

Files like the example: $0.81 810 API credits · ≈ ₽86.92 your files are measured before the run Run it on this page

Get API key

Made on Doitong

Public works made with Wan v22 Large by the Doitong community. Reuse a prompt in one click.

Public works shown: 3
Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-аним... Video

Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-анимация, весёлый водитель в кепке, крупные машины, пастельные цвета. 0:00–0:10 приветствие под музыку; 0:10–0:30 песенка: "Машина едет би-би, би-би", "Поезд едет ту-ту, ту-ту". Бодрая детская музыка...

Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-аним... Video

Создай 30-секундный обучающий музыкальный ролик для детей 3–5 лет. Тема: транспорт. Яркая 2D-анимация, тот же весёлый водитель в кепке, самолёт. 0:00–0:15 песенка: "Самолёт летит вж-ж-ж, вж-ж-ж"; 0:15–0:25 интерактивная пауза: водитель спрашивает "Как гудит машина?", пауза; 0:25–0:30 финальный...

# PROMPT: Animated Mother’s Day greeting card **Format:** vertical video 9:16 **Duration:** 12–15... Video

# PROMPT: Animated Mother’s Day greeting card **Format:** vertical video 9:16 **Duration:** 12–15 seconds **Style:** high‑quality Pixar‑inspired 3D animation, cinematic, warm, emotional, charming animated movie aesthetic. ### The main character is a child Use the attached image as the only and...

Build a request

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

•required

Text instructions that guide video generation.

•required video_url
Drop a file, or

Input video's URL.

resolution default 720p

Output video resolution: 480p, 580p, or 720p.

aspect_ratio default auto

Set the generated video's proportions explicitly, or choose 'auto' to let the input video determine them automatically.

default 81

Frame count for generation, with an inclusive range of 17–161.

default 1

Insert 0–4 interpolated frames into every gap between two generated frames.

Advanced negative_prompt · acceleration · interpolator_model · video_quality · video_write_mode · strength · frames_per_second · num_inference_steps · guidance_scale · guidance_scale_2 · shift · seed · enable_safety_checker · enable_output_safety_checker · enable_prompt_expansion · adjust_fps_for_interpolation · resample_fps
default

Negative prompt applied when generating a video.

acceleration default regular

Acceleration setting, with 'regular' as the recommended choice. Increasing acceleration sacrifices quality to shorten generation time.

interpolator_model default film

Frame interpolation setting: choose None to skip interpolation, or specify the model to perform it.

video_quality default high

Output video quality setting that trades larger files for improved visuals as the setting increases.

video_write_mode default balanced

Video writing mode, with balanced offering a compromise between speed and quality. Choose small for the smallest files and slowest writing; faster writing returns results sooner but creates larger files.

default 0.9

Video transformation strength, ranging in effect from an unchanged input at 0.0 to output based entirely on the prompt at 1.0.

default 16

Generated video frame rate, accepting values from 4 to 60; setting `adjust_fps_for_interpolation` to false preserves this rate unchanged. With interpolation in use and `adjust_fps_for_interpolation` true (its default), multiply this rate by one plus the interpolated frame count to obtain the final FPS. For example, 16 FPS with 1 interpolated frame becomes 32 FPS.

default 27

Sampling step count, trading longer processing time for better quality as the count increases.

default 3.5

Classifier-free guidance strength, trading possible quality loss for closer prompt matching as the scale increases.

default 4

Guidance scale controlling how closely the model follows the prompt during its second stage.

default 5

Video shift setting, with an allowed range of 1.0–10.0.

Seed that makes generation reproducible. Setting it to None selects a seed randomly.

POST /run/wan/v2.2-a14b/video-to-video?wait=20 quote → $0.81
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/wan/v2.2-a14b/video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/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 Wan · v2.2 A14b · Video to Video

Transforms an input `video_url` following a `prompt`. `strength` from 0 to 1 sets how far the result departs from the source: 0 keeps the input, 1 follows the prompt fully. Aspect ratio defaults to auto and matches the input. Resolution is 480p to 720p, `num_frames` 17 to 161, and `resample_fps` optionally resamples the video.

Parameters

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

NameType DefaultAllowed Description
video_urlrequired video
Typeurl · video
Input video's URL.
promptrequired
Typestring
Text instructions that guide video generation.
strengthoptional
Typenumber
Default0.9
0 – 1
Video transformation strength, ranging in effect from an unchanged input at 0.0 to output based entirely on the prompt at 1.0.
num_framesoptional
Typeinteger
Default81
17 – 161
Frame count for generation, with an inclusive range of 17–161.
frames_per_secondoptional
Typeinteger | null
Default16
4 – 60
Generated video frame rate, accepting values from 4 to 60; setting `adjust_fps_for_interpolation` to false preserves this rate unchanged. With interpolation in use and `adjust_fps_for_interpolation` true (its default), multiply this rate by one plus the interpolated frame count to obtain the final FPS. For example, 16 FPS with 1 interpolated frame becomes 32 FPS.
negative_promptoptional
Typestring
Default
Negative prompt applied when generating a video.
seedoptional
Typeinteger | null
Seed that makes generation reproducible. Setting it to None selects a seed randomly.
resolutionoptional
Typeenum
Default720p
480p580p720p
Output video resolution: 480p, 580p, or 720p.
aspect_ratiooptional
Typeenum
Defaultauto
auto16:99:161:1
Set the generated video's proportions explicitly, or choose 'auto' to let the input video determine them automatically.
num_inference_stepsoptional
Typeinteger
Default27
2 – 40
Sampling step count, trading longer processing time for better quality as the count increases.
enable_safety_checkeroptional
Typeboolean
Defaultfalse
Input safety screening before processing, which only authorized accounts may turn off. Requests lacking authorization are always screened; otherwise, true enables screening.
enable_output_safety_checkeroptional
Typeboolean
Defaultfalse
Controls safety screening of the generated video; setting true enables a check after generation.
enable_prompt_expansionoptional
Typeboolean
Defaultfalse
Allow a large language model to enrich the prompt with details. Enabling this expansion leaves the prompt's meaning unchanged.
accelerationoptional
Typeenum
Defaultregular
noneregular
Acceleration setting, with 'regular' as the recommended choice. Increasing acceleration sacrifices quality to shorten generation time.
guidance_scaleoptional
Typenumber
Default3.5
1 – 10
Classifier-free guidance strength, trading possible quality loss for closer prompt matching as the scale increases.
guidance_scale_2optional
Typenumber
Default4
1 – 10
Guidance scale controlling how closely the model follows the prompt during its second stage.
shiftoptional
Typenumber
Default5
1 – 10
Video shift setting, with an allowed range of 1.0–10.0.
interpolator_modeloptional
Typeenum
Defaultfilm
nonefilmrife
Frame interpolation setting: choose None to skip interpolation, or specify the model to perform it.
num_interpolated_framesoptional
Typeinteger
Default1
0 – 4
Insert 0–4 interpolated frames into every gap between two generated frames.
adjust_fps_for_interpolationoptional
Typeboolean
Defaulttrue
Frame-rate adjustment toggle: false preserves the supplied FPS, whereas true scales it by one plus the interpolated frame count. Thus, 16 FPS becomes 32 FPS when 1 frame is interpolated and adjustment is enabled.
video_qualityoptional
Typeenum
Defaulthigh
lowmediumhighmaximum
Output video quality setting that trades larger files for improved visuals as the setting increases.
video_write_modeoptional
Typeenum
Defaultbalanced
fastbalancedsmall
Video writing mode, with balanced offering a compromise between speed and quality. Choose small for the smallest files and slowest writing; faster writing returns results sooner but creates larger files.
resample_fpsoptional
Typeboolean
Defaultfalse
Whether video resampling is disabled (false) or performed at the supplied frame rate (true).
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": "wan/v2.2-a14b/video-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": 810,
    "usd": "0.81",
    "charged": 810,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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
    },
    "prompt": "A low-angle medium shot captures a domestic white cat with brown and black patches and a blue bandana sitting on a light-colored tiled floor indoors, meticulously grooming itself by licking its paw and then rubbing its face with it, against a soft-focused background of wooden kitchen cabinets and a reflective metallic appliance.",
    "seed": 42
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/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 file produced by generation.
prompt
stringText prompt used to generate the video.
seed
integerSeed value applied during generation.

More models: Video to Video

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/wan/v2.2-a14b/video-to-video.md. All models and guides: https://doitong.com/developers/llms.txt