FLUX 3 Image to Video API

blackforestlabs/flux-3/image-to-video

FLUX 3 Image to Video turns one start image and a text prompt into 5–20 seconds of high-fidelity video, with realistic physical motion, camera control, and optional synchronized native audio. It faithfully preserves the source subject, clothing detail, and lighting composition while smoothly expanding action, camera moves, and soundscape from your prompt.

Input

Prompt

152/20000

Start frame

Add start

Upload the required image.

Duration

Resolution

Aspect ratio

Sound

Output

Idle

Your generated video will appear here

Add your prompt and required media, review the settings, then click Run.

Continue with

FLUX 3 Text to Video FLUX 3 First Last Frame to Video FLUX 3 Extend Video FLUX 3 Keyframes to Video

Examples

The subject turns their head slightly toward the camera with a calm expression while a warm breeze gently moves their collar. Preserve the same face, clothing, window light, and background. Camera: locked medium close-up. Native audio: soft outdoor breeze and quiet room tone. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

A sudden countryside gust lifts the cream sheet and the faded shirt on the line; they billow and slap, then settle. Preserve the same posts, yard, dusk light, and camera. Camera: locked wide shot. Native audio: fabric slap, dry grass wind, distant insects. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

Steam rises from the tea cup in slow curling ribbons and drifts toward the open window; dust motes shimmer in the morning light. Preserve the same cup, book, windowsill, and lighting. Camera: locked close shot. Native audio: a faint breeze, a distant kettle tick, quiet room tone. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.

REST API

Quick Start

Authenticate with the API, submit the start image and instructions, then retrieve the video using the task ID.

Connect to the Vidgo API

Create an API key, keep it only on your server, and send Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one generation task

Fill in the inputs and settings for this endpoint using the request example, then save the returned task_id to query generation progress and results.

Submit request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "blackforestlabs/flux-3/image-to-video",
  "input": {
    "prompt": "The subject turns their head slightly toward the camera with a calm expression while a warm breeze gently moves their collar. Preserve the same face, clothing, window light, and background. Camera: locked medium close-up. Native audio: soft outdoor breeze and quiet room tone. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "auto",
    "sound": true,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-3/image-to-video/v1/01/input-start-frame.webp"
    ]
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Wait for the result

Query with task_id, continue for not_started/running, and stop for finished/failed. On success, read data.files[].file_url.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll status with a 2-second base interval, and increase the interval for longer tasks. Continue only while status is not_started or running, and stop once finished or failed. You can also specify callback_url in the request payload to receive webhook notifications.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "running",
    "created_time": "2026-09-16T10:00:00Z"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete runnable example

Expand for a complete script with HTTP and business-code checks, task_id validation, polling, terminal-state handling, and a timeout boundary.

Complete runnable example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "blackforestlabs/flux-3/image-to-video",
  "input": {
    "prompt": "The subject turns their head slightly toward the camera with a calm expression while a warm breeze gently moves their collar. Preserve the same face, clothing, window light, and background. Camera: locked medium close-up. Native audio: soft outdoor breeze and quiet room tone. No logos, no readable text, no products, no packaging, no prices, no CTA, no advertising, no watermark, no brand marks.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "auto",
    "sound": true,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-3/image-to-video/v1/01/input-start-frame.webp"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input parameters

The table lists available input parameters, types, and defaults. Request examples also include the required top-level model field. Prepare the start image and configure the output.

Field	Type	Required	Default	Description
prompt	string	Yes	—	Minimum length 1. Directs subject action, camera movement, visual change, and sound after the start frame.
image_urls	string[]	Yes	—	Array containing exactly one publicly accessible image URL as the opening frame.
duration	integer	No	5	Output video duration from 5–20 seconds.
resolution	string	No	720p	Output resolution: 720p or 1080p.
aspect_ratio	string	No	auto	Framing ratio: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.
sound	boolean	No	true	Whether to generate native audio: true or false.

Response Fields

A successful submission returns a task ID. Status queries provide progress, output files, and error details when a task fails.

Field	Type	Description
code	integer	Application result code; successful responses use 0 or 200.
message	string	Human-readable message or error detail when present.
data.task_id	string	Task ID used in the status endpoint path.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation time in date-time format.
data.progress	integer	Task progress from 0 to 100, when included in the response.
data.files[]	array	All output files from a successful task, in response order.
data.files[].file_url	string	Public URL for a generated video.
data.files[].file_type	string	File type, such as video.
data.error_message	string \| null	Failure detail when status is failed.

Task Lifecycle

Continue querying while the status is not_started or running. End polling at finished or failed, then process the output files or error details respectively.

not_started
The task was accepted and is waiting to begin.
running
Generation is in progress. Continue polling the same task_id.
finished
Generation succeeded. Read every video URL from data.files[].file_url.
failed
Generation stopped with an error. Read data.error_message and stop polling.

Polling and Errors

AuthenticationFor a 401 response, check the Bearer API key in Authorization, update the credentials, and retry.
ValidationFor a 400 response, use the response details to check required inputs, parameter values, and available credits, then make the indicated adjustments before submitting again.
Network and timeoutIf a status query encounters a network error or timeout, retain the original task_id and retry the query, then handle the result according to the returned task status.
Polling intervalPoll status with a 2-second base interval, and gradually increase the interval for longer tasks.
Terminal statesContinue only for not_started or running. Stop immediately on finished or failed.
Callback optionProvide callback_url at the request top level to receive the final flat task object; polling remains available if delivery fails.

Endpoint limits

Specification	Value	Details
Input mode	Prompt + 1 image	Exactly one start image URL and a motion prompt.
Output	Video with optional native audio	The endpoint returns an asynchronous task ID.
Duration	5–20 seconds	Integer range; default is 5 seconds.
Resolution	720p / 1080p	Default is 720p.
Aspect ratio	8 options (including auto)	auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16; default auto.
Billing basis	Output seconds × resolution rate	720p: 34 credits/sec; 1080p: 58 credits/sec.

View FLUX 3 Image to Video API documentation

FLUX 3 Image to Video

FLUX 3 Image to Video uses a single still frame as the visual starting point and a text prompt to create a continuous clip with optional native audio. It carries forward subject identity, material texture, and ambient lighting from the opening image, with 5–20 second duration, 8 aspect ratios, and 720p / 1080p output.

Why Choose This?

Physics-driven motion from a stillAnchor on the subject, lighting, and composition of the start frame, then inject realistic physical motion that brings product art, portraits, or scene stills to life.
Native audio-visual syncAutomatically infer and match ambient effects and dynamic soundscapes, with sound toggling native audio on or off.
Faithful subject and composition carryoverParse facial structure, wardrobe texture, and spatial lighting so identity and framing stay stable as motion unfolds.
Prompt-directed action and cameraDescribe a head turn, fabric sway, push-in, or orbit so the existing image develops around a clear momentum plan.
5–20 second high-fidelity takesGenerate continuous action from 5 to 20 seconds for micro-expressions, product reveals, and narrative blocking.
Flexible framing and clarity tiersChoose among 8 aspect ratios including auto, plus 720p and 1080p resolution for multi-channel delivery.

Parameters

Parameter	Requirement	Description
prompt	Required	String with minimum length 1. Directs subject action, camera movement, visual change, and sound after the start frame.
image_urls	Required	String array containing exactly one publicly accessible image URL used as the opening frame and visual anchor.
duration	Optional	Integer. Sets output length from 5–20 seconds; the Playground preselects 5 seconds. Default`5`
resolution	Optional	String. Sets output resolution to 720p or 1080p; the Playground preselects 720p. Default`720p1080p`
aspect_ratio	Optional	String. Controls framing, supporting auto and common landscape/portrait ratios; the Playground preselects auto. Default`auto21:92:116:94:31:13:49:16`
sound	Optional	Boolean. Controls whether native audio is generated; the Playground preselects true. Default`truefalse`

How to Use

Provide a start image URLSupply one publicly accessible image URL with a clear subject and composition in image_urls as the opening baseline.
Describe action, camera, and soundIn prompt, write the subject motion, camera move, and ambient or action audio that should develop from the start frame.
Choose a durationPick an integer length between 5 and 20 seconds, with 5 seconds selected by default, to match the main action and pacing.
Set resolution and framingChoose 720p or 1080p and an aspect ratio for your delivery format, or keep auto to follow the start frame.
Confirm the sound settingKeep sound as true for synchronized native audio, or set it to false for picture-only output.
Review the cost and runReview the cost shown on the Run button, complete the required inputs and prompt, then click Run.
Preview and download the videoWhen the task finishes, preview the video and sound in the output panel, then download the result.

Pricing

Billed by output video seconds and resolution tier, with synchronized native audio included in the result. 1 credit = $0.005.

Usage	Rate	Details
720p	34 credits/sec ($0.17/sec)	Default 5s at 720p is 170 credits ($0.85).
1080p	58 credits/sec ($0.29/sec)	5s at 1080p is 290 credits ($1.45).

Best Use Cases

Animated product visualsUse a product still as the start frame and describe camera movement and material reflections for brand presentation footage.
Portrait and character animationStart from a portrait and design head turns, expressions, or clothing motion so static characters enter the shot naturally.
Concept art and illustration motionAdd wind, drifting clouds, and shifting light to scene art, with matching natural ambient sound.
Social vertical contentTurn selected photography into 9:16 short videos with native audio for multi-platform publishing.

Pro Tips

Choose a start image with a clear subject outline, lighting, and composition to establish the visual starting point.
Describe action that continues from what is already visible, such as “The person raises their cup as the camera slowly moves closer.”
State facial features, clothing, or setting details to carry forward in one sentence, then specify camera motion separately.
When describing momentum, include start, finish, and pacing—for example, “slowly turns, then holds a gaze toward camera.”
Tie sound cues to visible events and setting, such as “Audio: soft outdoor breeze and natural ambient sound.”

Usage notes

FLUX 3 Image to Video generates video from one start image and a text prompt, using prompt and image_urls as its main inputs. Duration, resolution, aspect ratio, and sound configure the output.
When sound is true, native synchronized audio is included; you can also add ambient or action-sound cues in the prompt.
Use publicly accessible HTTP(S) URLs for API media inputs so the service can retrieve the files.
Save the task_id returned by an API submission to query progress and retrieve the result.

Related Endpoints

FLUX 3 Text to VideoGenerate a 5–20 second clip with optional native audio from a text prompt only.

FLUX 3 First Last Frame to Video preview

FLUX 3 First Last Frame to VideoInterpolate a coherent transition between required start and end frames.

FLUX 3 Extend VideoContinue an existing MP4 from its final frame for 5–20 new seconds.

FLUX 3 Keyframes to VideoPlace 1–10 keyframes on a 24 fps timeline to direct a multi-shot take.

Gemini Omni 1.1 FlashUse Google Gemini Omni 1.1 Flash for text, frame, reference, and video-edit workflows with native audio.

Seedance 2.5Compare a ByteDance family with text, start/end-frame, and multimodal reference workflows.

MiniMax H3Compare a fixed 2K video family with text, frame, and multimodal reference workflows.

FLUX 3 Image to Video API frequently asked questions

What is the FLUX 3 Image to Video API?

FLUX 3 Image to Video is a Black Forest Labs image-to-video model. It takes one start image and a text prompt to generate 5–20 seconds of high-fidelity continuous action video, with optional synchronized native audio that automatically matches ambient effects and dynamic soundscapes. Anchored on the still’s subject, lighting, and composition, it smoothly injects realistic physical motion while faithfully preserving the opening frame’s framing, clothing detail, and illumination. You can call it programmatically or try it from the playground above.

How does FLUX 3 Image to Video keep facial and clothing consistency from a still?

The model anchors facial structure, wardrobe texture, and spatial lighting from the start image. Use a clear, detailed source still, emphasize appearance traits to carry forward in the prompt, then separately describe actions such as a head turn or raised hand to guide motion without rewriting identity.

How should I describe action momentum in a FLUX 3 Image to Video prompt?

Continue from what is already visible in the frame and state start, finish, and pacing—for example, “slowly turns, then holds a gaze toward camera as a breeze moves the collar.” Add camera push-ins or orbits so physical inertia and framing change share one timeline.

Does FLUX 3 Image to Video automatically generate matching ambient audio?

Yes. When sound is true, the model infers ambient effects and dynamic soundscapes from the start-frame setting and action cues in the prompt. You can also append specific sound notes at the end of the prompt, such as outdoor breeze or room tone.

How should a still’s framing match FLUX 3 Image to Video aspect_ratio?

Set aspect_ratio to auto to follow the start image’s width-to-height ratio. Choosing a fixed ratio such as 16:9 or 9:16 adapts the composition while keeping the subject centered for your target publishing format.

How does the sound field control native audio in FLUX 3 Image to Video?

sound defaults to true and includes synchronized native audio in the result; set it to false for picture-only output. With audio enabled, add dialogue, ambient, or action-sound cues in the prompt so the soundtrack aligns with visible motion.

When should I pair FLUX 3 Image to Video with end-frame control?

This endpoint focuses on evolving action and camera from a single opening still. If you need to anchor both the start and closing compositions, use FLUX 3 First Last Frame to Video with two ordered frames for dual-anchor transition generation.