Skip to content

Cosmos Predict 2.5 2B · Image to Video

Integrate

Model id cosmos-predict-2.5/image-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/cosmos-predict-2.5/image-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",
    "image": "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"

This request: $0.20 200 API credits Run it on this page

Get API key
NVIDIA · 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 description of the desired video.

•required image_url
Drop a file, or

URL pointing to the image used as the initial frame.

Advanced negative_prompt · video_output_type · video_quality · num_frames · num_inference_steps · guidance_scale · seed · enable_safety_checker
default The video captures a ...

Negative prompt specifying unwanted content to steer generation away from.

video_output_type default X264 (.mp4)

Format for the resulting video.

video_quality default high

Quality setting for the resulting video.

default 93

Frame count for generation, ranging from 9 to 93.

default 35

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

default 7

Scale for classifier-free guidance; increasing it makes generation follow the prompt more closely.

Random seed that makes generation reproducible.

POST /run/cosmos-predict-2.5/image-to-video?wait=20 quote → $0.20
# 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/cosmos-predict-2.5/image-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",
    "image": "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 Cosmos Predict 2.5 2B · Image to Video

Animates `image_url`, used as the first frame, following a text `prompt`. `num_frames` is 9 to 93, `num_inference_steps` up to 50 (default 35) and `guidance_scale` 1 to 20. Output formats are mp4, webm, mov or GIF, with four quality levels.

Parameters

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

NameType DefaultAllowed Description
promptrequired
Typestring
Text description of the desired video.
negative_promptoptional
Typestring
DefaultThe video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.
Negative prompt specifying unwanted content to steer generation away from.
num_framesoptional
Typeinteger
Default93
9 – 93
Frame count for generation, ranging from 9 to 93.
num_inference_stepsoptional
Typeinteger
Default35
1 – 50
Denoising step count, trading longer processing for better quality as the count increases.
guidance_scaleoptional
Typenumber
Default7
1 – 20
Scale for classifier-free guidance; increasing it makes generation follow the prompt more closely.
seedoptional
Typeinteger | null
Random seed that makes generation reproducible.
video_output_typeoptional
Typeenum
DefaultX264 (.mp4)
X264 (.mp4)VP9 (.webm)PRORES4444 (.mov)GIF (.gif)
Format for the resulting video.
video_qualityoptional
Typeenum
Defaulthigh
lowmediumhighmaximum
Quality setting for the resulting video.
enable_safety_checkeroptional
Typeboolean
Defaulttrue
Screening can be relaxed by setting false, provided the caller is authorized.
image_urlrequired image
Typeurl · image
URL pointing to the image used as the initial frame.
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": "cosmos-predict-2.5/image-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": 200,
    "usd": "0.20",
    "charged": 200,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "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.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, width, height, fps, duration, num_frames}Video file produced by generation.
seed
integerSeed that controlled randomness during generation.

More models: Image to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/cosmos-predict-2.5/image-to-video.md. All models and guides: https://doitong.com/developers/llms.txt