PixVerse V6 API

About PixVerse V6

pixverse/v6/image-to-video takes image_url as the first frame and an optional last_image_url as the ending. The clip travels from one picture to the other, so both should show the same subject at a comparable scale.

Call it with the model name pixverse/v6/image-to-video on POST /jobs/createTask, from $0.111.

Introduction

PixVerse V6 Image to video animates a first frame into a clip of 1 to 15 seconds at 360p, 540p, 720p or 1080p. Add last_image_url and the clip moves from the first image to the last one. The prompt is required and describes what happens. The clip keeps the aspect ratio of your first image. Images are JPG, JPEG, PNG or WebP, up to 20 MB each.

Choose a PixVerse V6 mode by starting material

Key features

First frame, optional last frame

image_url sets the opening and last_image_url the ending. In our test a woman in a rust coat at the open slit of a white observatory dome (first frame) and the same woman leaning back on the railing with her arms crossed (last frame) became one move: she turns, walks along the railing, leans back and crosses her arms, and the clip ends on the last frame.

The shape follows your image

There is no aspect-ratio field. A portrait image comes back as a portrait clip, a wide image as a wide clip.

A multi-shot switch

shot_type is single by default. Set multi to let the model cut the clip into several shots. It cannot be combined with a last frame.

Sound when you want it

generate_audio is off by default. On, the model generates ambience, effects, music and any dialogue you write in quotes.

Request parameters

Pricing

Prices are in USD. The API uses a separate USD balance. Website credits cannot be used or transferred to it, and API funds cannot be transferred to website credits. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

Bring a still to life

A portrait, a street scene or a frame saved from an earlier clip. Describe what happens next and the person, wardrobe and setting come from the image.

Move between two poses

Give a last frame that differs from the first and let the model fill in the move, as in our observatory example.

Keep a character across shots

Save a frame from one clip and use it as the first frame of the next to carry a person and a set from shot to shot.

Prompt guide & pro tips

Describe the motion, not the picture

The image already shows what everything looks like. Spend the prompt on the action, the camera move and, if audio is on, the sound.

Keep both frames consistent

Use the same person and set in the first and the last frame. Frames that disagree leave the model no natural move between them.

Give each beat room

In our gas-station test the prompt listed a lamp, a map, a walk and a passing truck; the man folded the map, tucked it away and walked to the car, and the truck with its headlights on appeared in the last second of the 5-second clip. Ask for fewer beats, or add seconds, if a late beat matters.

Compare with a seed

seed keeps runs comparable while you change one thing at a time. It does not guarantee identical frames.

API quick start

Call the PixVerse V6 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls use your separate USD balance.
2. Send the request. POST /jobs/createTask with model pixverse/v6/image-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. 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": "pixverse/v6/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",
    "resolution": "720p",
    "duration_seconds": 5,
    "shot_type": "single"
  }
}'

# 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.

About the PixVerse V6 Image to Video endpoint

The output shape follows image_url. The endpoint has no aspect_ratio field, so crop the still to the frame you want before upload. JPG, JPEG, PNG and WebP up to 20 MB are accepted.

last_image_url cannot be combined with shot_type multi. Send one or the other; a body with both is rejected as invalid_request.

The prompt describes what happens between the frames, or after the first one when only image_url is sent. With generate_audio on, name the sound and put any dialogue in quotes.

PixVerse V6 API questions

More about PixVerse V6

Try it

PixVerse V6 AI Video Generator onlineCreate videos with PixVerse V6 in PopNow

Endpoints

All PixVerse V6 endpoints and pricing

Endpoints

PixVerse V6 · Create VideoPixVerse V6 · Reference to VideoPixVerse V6 · Extend Video

Docs

PixVerse V6 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get PixVerse V6 results without polling