About FLUX 3
FLUX 3 image-to-video animates a first frame, with an optional last frame to move toward, adding synchronized sound, in clips of 5 to 20 seconds.
Call it with the model name black-forest-labs/flux-3/image-to-video on POST /jobs/createTask, from 45 credits for a 5-second clip ($0.45). New accounts get 30 free credits to try it in the Playground first.
Introduction
FLUX 3 Image to video animates a still image with Black Forest Labs' FLUX 3 video model. Give it an opening frame and, if you like, a closing frame; it writes 5 to 20 seconds of motion with synchronized sound at 720p or 1080p.
Choose a mode by starting material
| What you have | Mode |
|---|---|
| a written brief | FLUX 3 Text to video |
| a still to animate, with an optional last frame | FLUX 3 Image to video |
| a clip to continue | FLUX 3 Video extend |
| a clip to enlarge | FLUX 3 Video upscale |
Key features
The image sets the look
The person, outfit and setting come from the opening frame, so the prompt only has to describe the action, the camera and the sound.
Opening and closing frame
With a last image the clip moves from one to the other. Frames that are close in light and position blend smoothly; frames that are far apart can produce a hard cut in the middle.
Shape follows the image
Leave the aspect ratio out and the clip keeps the shape of the opening frame.
Request parameters
| Parameter | Required | Description |
|---|---|---|
aspect_ratio | No | The shape of the frame: wide, square or tall. 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9 · 2:1 |
duration_seconds | No | How long the clip runs. You pay per second. 5–20 · Default: 5 |
generate_audio | No | Adds sound made to match the picture: voices, ambience and effects. Default: true |
image_url | Yes | The picture to start from. |
last_image_url | No | Optional final frame, so the clip ends exactly where you want. |
prompt | Yes | Describe the subject, action, camera, light and sound for the shot. |
quality | No | Trades speed and price for finer detail. standard · draft · Default: standard |
resolution | No | Output size. Bigger sizes look sharper and cost more. 720p · 1080p · Default: 720p |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per second | ≈ USD |
|---|---|---|
| quality draft · resolution 1080p | 9 | $0.09 |
| quality draft · resolution 720p | 9 | $0.09 |
| quality standard · resolution 720p | 25.5 | $0.26 |
| quality standard · resolution 1080p | 43.5 | $0.44 |
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
Bringing portraits to life
A smile, a turn of the head, wind in hair, with matching room sound.
Before-and-after moves
Time-of-day shifts or a pose change from a start frame to an end frame.
Product and location stills
A slow camera arc around a subject you already have a picture of.
Prompt guide & pro tips
Describe motion, not the picture
The image already shows who and where; write what changes.
Keep the two frames close
Similar light and placement make a smooth move; very different frames tend to be joined by a cut.
Do not rely on one-shot wording
Asking for one continuous shot does not guarantee it, so check the result.
Expect small face drift on long moves
The face can shift slightly during big head turns or when hands cross it.
Preview at draft
Test the motion at draft before a full render.
API quick start
Call the FLUX 3 API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model black-forest-labs/flux-3/image-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "black-forest-labs/flux-3/image-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"quality": "standard",
"resolution": "720p",
"duration_seconds": 5
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
FLUX 3 API questions
How much does the FLUX 3 API cost?
FLUX 3 starts at 45 credits ($0.45) for a 5-second clip with Image to Video, its cheapest task. Prices by option: draft · 1080p 9 credits per second, draft · 720p 9 credits per second, standard · 720p 25.5 credits per second, standard · 1080p 43.5 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for FLUX 3 in the API?
Put black-forest-labs/flux-3/text-to-video for Create Video; black-forest-labs/flux-3/image-to-video for Image to Video; black-forest-labs/flux-3/video-extend for Extend Video; black-forest-labs/flux-3/upscale for Upscale Video in the model field of POST /jobs/createTask.
Does video extend return the whole clip?
No. The result contains only the newly generated segment, not your source clip, so join the two in an editor. The new segment starts from the last frame of the source; in our test it began with a short dissolve and then moved on to the next action.
Can I make one long 20 second shot?
You can ask for up to 20 seconds, but the model may still cut or dissolve inside a clip, especially when the light or the action changes a lot. For control, make shorter clips and chain them with extend.
Can I give it a last frame?
Yes, on image to video. The clip moves from the first image to the last. If the two frames differ a lot in light or place, the model may use a hard cut in the middle rather than a gradual change, so keep the frames close when you want a smooth move.
What are the limits of the FLUX 3 API?
Clip length: 5–20 s; Resolutions: 720p · 1080p; Aspect ratios: 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9 · 2:1; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.
Can I try FLUX 3 without writing code?
Yes. The Playground runs FLUX 3 on your PopNow credits, needs no API key, and shows the matching code for every run.
All FLUX models
LTX 2.5 reaches 4K natively and also runs 20 seconds. FLUX 3 adds a cheap draft tier plus extend and upscale in one place.
- FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
- FLUX 3 APIVideo with synced sound and a quick draft tierFrom 45 credits for a 5-second clip
- FLUX.2 Klein 9B LoRA APIFast FLUX.2 Klein 9B that loads up to three of your LoRAsFrom 3 credits per image
- FLUX.2 Klein Base 9B LoRA APIUndistilled Klein 9B for varied looks with your LoRAsFrom 4 credits per image
- FLUX.2 Klein 4B LoRA APISmall, quick FLUX.2 Klein 4B with your own LoRAsFrom 3 credits per image
- FLUX.2 Klein Base 4B LoRA APIUndistilled Klein 4B that loads your own LoRAsFrom 3 credits per image
- FLUX.2 Klein 9B APIFast FLUX edits that keep faces and poses intactFrom 2 credits per image
- FLUX.2 Klein 4B APIThe smallest, quickest FLUX for rapid draftsFrom 2 credits per image
- FLUX.2 Dev LoRA APIFLUX.2 Dev images and edits with your own LoRAsFrom 4 credits per image
- FLUX.2 Pro APIPhotoreal images with readable text and hex color controlFrom 5 credits per image
- FLUX.2 Flex APISpells headlines and labels exactly as writtenFrom 9 credits per image
- FLUX.2 Dev APIOpen-weights FLUX that can merge people into one sceneFrom 2 credits per image
- FLUX.1 Krea Dev LoRA APIPhotographic FLUX.1 Krea with your own LoRAsFrom 4 credits per image
- FLUX.1 Dev ControlNet LoRA APIPose, depth or edge control on FLUX.1 with your LoRAsFrom 6 credits per image
- FLUX.1 Fill Dev LoRA APIMasked inpainting on FLUX.1 Fill with your own LoRAsFrom 7 credits per image
- FLUX.1 Dev LoRA APIClassic FLUX.1 Dev with up to three of your LoRAsFrom 3 credits per image
- FLUX.1 Schnell LoRA APIFast FLUX.1 Schnell that loads your own LoRAsFrom 1 credit per image