PixVerse V6 Reference to Video creates high-quality videos from prompts, up to 10 reference images, and up to 2 reference videos. Use image references for subject, product, character, and scene consistency, and video references for motion, camera movement, action timing, and visual style. Supports optional audio and up to 1080P output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
就緒

$1每次運行
PixVerse V6 Reference-to-Video creates high-quality videos from a text prompt and visual references. Provide up to 10 reference images and up to 2 reference videos, then describe how the subjects, scene, action, camera movement, and visual style should be combined into the final clip.
This model is designed for Fusion-style generation: it can preserve the identity or look of reference subjects, borrow scene or motion cues from uploaded references, and use your prompt to compose them into a coherent video. It supports multiple resolution tiers up to 1080p and optional audio generation.
Image and video reference control
Use reference images for subject, character, product, background, or style consistency, and use video references for motion, camera movement, scene rhythm, or visual style.
V6 Fusion generation
The model can understand subjects, actions, scenes, camera moves, and style cues from reference media, then modify or recombine them according to the prompt.
Up to 10 images and 2 videos
Add multiple image references for richer composition, plus up to 2 reference videos when you need stronger motion or scene guidance.
Optional audio generation
Enable generate_audio_switch to create synchronized audio for the generated video.
Flexible resolution choices
Choose auto, 360p, 540p, 720p, or 1080p depending on preview speed, quality target, and publishing needs.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the final video, including subject behavior, scene details, motion, camera movement, and style. When using named references in your prompt, make the relationship between each reference and the scene clear. |
| images | No | Reference image URLs. Supports up to 10 images. Use these for subject identity, character appearance, product details, background, costume, object, or style references. |
| videos | No | Reference video URLs. Supports up to 2 videos per request. The total duration of all reference videos must not exceed 15 seconds. Use these for action, motion, camera movement, scene rhythm, or video style references. |
| duration | No | Target clip length in seconds when no reference video is provided. Default: 5. In the current model schema, this parameter accepts 1–10. When videos are provided, set duration to 0; the output duration follows the reference video duration. |
| resolution | No | Output resolution: auto, 360p, 540p, 720p, or 1080p. Default: 720p. |
| generate_audio_switch | No | Whether to generate synchronized audio for the output video. Default: false. |
images when visual identity matters, such as the same person, product, outfit, prop, background, or style.videos when motion matters, such as dance movement, handheld camera feel, product rotation, action timing, or scene pacing.duration to 0.360p or 540p for faster iteration, then switch to 720p or 1080p for higher-quality output.generate_audio_switch when the scene benefits from ambience, impact sounds, crowd noise, weather, or other synchronized audio.Pricing is calculated per generated second. Billed duration is rounded up to the next whole second, with a minimum of 5 seconds and a maximum of 15 seconds. When videos are provided, pricing uses the video-reference rate. auto is charged at the same rate as 360p.
| Resolution | No Audio | With Audio |
|---|---|---|
| auto / 360p | $0.025/s | $0.035/s |
| 540p | $0.035/s | $0.045/s |
| 720p | $0.045/s | $0.060/s |
| 1080p | $0.090/s | $0.115/s |
| Resolution | No Audio | With Audio |
|---|---|---|
| auto / 360p | $0.050/s | $0.070/s |
| 540p | $0.070/s | $0.090/s |
| 720p | $0.090/s | $0.120/s |
| 1080p | $0.180/s | $0.230/s |
| Scenario | Cost |
|---|---|
| 10s, 720p, no audio, without video references | $0.45 |
| 10s, 720p, with audio, without video references | $0.60 |
| 6s reference video, 1080p, no audio | $1.08 |
| 6s reference video, 1080p, with audio | $1.38 |
images, videos, or both.duration to 0. The output duration will automatically match the longest reference video.character01, product_ref, or motionRef instead of names with spaces.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pixverse/pixverse-v6/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Pixverse v6 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "auto",
"generate_audio_switch": false
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/pixverse/pixverse-v6/reference-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/pixverse/pixverse-v6/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "auto",
"generate_audio_switch": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "auto",
"generate_audio_switch": False
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/pixverse/pixverse-v6/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Pixverse v6 Reference To Video is a Pixverse model for video generation from images, exposed as a REST API on WaveSpeedAI. PixVerse V6 Reference to Video creates high-quality videos from prompts, up to 10 reference images, and up to 2 reference videos. Use image references for subject, product, character, and scene consistency, and video references for motion, camera movement, action timing, and visual style. Supports optional audio and up to 1080P output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pixverse/pixverse-pixverse-v6-reference-to-video.
Pixverse v6 Reference To Video starts at $1.00 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `duration`, `generate_audio_switch`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/pixverse/pixverse-pixverse-v6-reference-to-video.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (Pixverse). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.