Skip to content

Flux 3 Keyframes To Video Draft

Integrate

Model id blackforestlabs/flux-3/keyframes-to-video/draft
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3/keyframes-to-video/draft?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",
    "keyframes": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "frame_index": 0
      }
    ]
  }'

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

This request: $0.30 300 API credits Run it on this page

Get API key
Black Forest Labs · 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 draft video.

duration 5 s

Draft length used to validate keyframe positions; an explicit whole-second value between 5 and 20 is required.

aspect_ratio default auto

Draft output's aspect ratio; `auto` delegates the choice to the model.

•required

Collection of at most 10 images, each assigned a different `frame_index` to fix its position within the generated draft.

Advanced safety_tolerance
default 2

Video safety tolerance uses a scale whose most permissive setting is 4 and whose strictest setting is 0.

POST /run/blackforestlabs/flux-3/keyframes-to-video/draft?wait=20 quote → $0.30
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://vit.doitong.com/api/v1/run/blackforestlabs/flux-3/keyframes-to-video/draft?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",
    "keyframes": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "frame_index": 0
      }
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://vit.doitong.com/api/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 Flux 3 Keyframes To Video Draft

Supply a `prompt` and 1 to 10 `keyframes`, each with a unique `frame_index`. An explicit `duration` of 5 to 20 seconds is needed so keyframe positions can be validated. `aspect_ratio` can be auto or range from 21:9 to 9:16, and `generate_audio` toggles sound. Output includes a `draft_cache` for a full-quality render.

Parameters

NameType DefaultAllowed Description
promptrequired
Typestring
Text description of the draft video.
aspect_ratiooptional
Typeenum
Defaultauto
auto21:92:116:94:31:13:49:16
Draft output's aspect ratio; `auto` delegates the choice to the model.
durationoptional
Typeenum
Default5
567891011121314151617181920
Draft length used to validate keyframe positions; an explicit whole-second value between 5 and 20 is required.
generate_audiooptional
Typeboolean
Defaulttrue
Controls audio generation for the draft video.
safety_toleranceoptional
Typeinteger
Default2
0 – 4
Video safety tolerance uses a scale whose most permissive setting is 4 and whose strictest setting is 0.
keyframesrequired
Typeobject[]
≤ 10 items
Collection of at most 10 images, each assigned a different `frame_index` to fix its position within the generated draft.
keyframes[].image_urlrequired
Typeurl · image
Keyframe image URL; accepts PNG, JPEG, or WebP.
keyframes[].frame_indexrequired
Typeinteger
≥ 0
Keyframe placement uses a distinct frame index for each keyframe, bounded above by `duration * 24`; the output runs at 24 fps.
required

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "blackforestlabs/flux-3/keyframes-to-video/draft",
  "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": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "keyframes": [
      {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "frame_index": 0
      }
    ]
  },
  "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
    },
    "draft_cache": {
      "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
    }
  },
  "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://vit.doitong.com/api/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://vit.doitong.com/api/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 produced as a draft.
draft_cache
object {url, content_type, file_name, file_size} | nullCache data for rendering a draft at full quality through `draft-enhance`, stored in a durable, encrypted bundle. This output is absent if the partner returned no bundle for the draft.

More models: Image to Video

For AI agents: this page as Markdown is at https://doitong.com/developers/models/blackforestlabs/flux-3/keyframes-to-video/draft.md. All models and guides: https://doitong.com/developers/llms.txt