Luma Ray 3.2 Video Edit is a fast AI video-to-video editing model that re-renders an existing source video from a text prompt while preserving the original motion and timing. Ready-to-use REST inference API for video restyling, creative edits, product videos, advertising creatives, social media clips, visual storytelling, and professional video editing workflows with simple integration, no coldstarts, and affordable pricing.
就緒
$0.72每次運行·~13 / $10
Change the clothe to ballet performance clothing.
Ray 3.2 Video Edit transforms an existing source video using a text prompt while preserving the original motion, timing, and scene structure. Upload a clip, describe the visual change you want, and generate an edited video in your selected resolution and duration.
Ray 3.2 Video Edit is ideal for restyling footage, changing visual atmosphere, modifying subjects or environments, and creating polished video variations without rebuilding the entire shot from scratch.
Motion-preserving video editing
Edit an existing video while keeping the original motion, pacing, camera movement, and overall timing intact.
Prompt-based visual control
Describe the exact style or change you want — from cinematic lighting and character appearance to environment, mood, material, or art direction.
Flexible output resolution
Choose between 540p, 720p, and 1080p depending on your quality needs, iteration speed, and budget.
Short-form video generation
Generate 5s or 10s outputs, making it suitable for fast creative iteration, social content, product previews, and visual experiments.
Simple editing workflow
Advanced edit controls are handled automatically, so you only need to provide the source video, prompt, and optional output settings.
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video to edit. Use a clear clip with visible subjects, stable framing, and consistent motion for best results. |
| start_image | No | Optional starting image used to guide the first frame or initial appearance of the edited video. |
| prompt | Yes | Text prompt describing how the source video should be edited. Be specific about style, subject changes, lighting, environment, and mood. |
| resolution | No | Output resolution: 540p, 720p, or 1080p. Default: 540p. |
| duration | No | Output duration: 5s or 10s. Default: 5s. |
Cinematic style edit:
Transform the video into a dramatic cyberpunk night scene with neon reflections, cinematic lighting, rain-soaked streets, and a high-contrast film look.
Character or outfit edit:
Keep the same motion and camera angle, but change the person’s outfit into a futuristic white space suit with subtle metallic details.
Environment edit:
Replace the background with a tropical beach at sunset, warm golden lighting, soft ocean waves, and a relaxed cinematic atmosphere.
Pricing depends on output resolution and duration.
| Duration | 540p | 720p | 1080p |
|---|---|---|---|
| 5s | $0.72 | $1.08 | $2.16 |
| 10s | $1.44 | $2.16 | $4.32 |
10s costs 2x the 5s price.720p costs 1.5x the 540p price.1080p costs 3x the 540p price.540p, 5s — $0.72.540p when iterating quickly, then move to 720p or 1080p for final outputs.5s for fast prompt testing and 10s when you need a longer finished clip.video and prompt are required fields.resolution defaults to 540p if not specified.duration defaults to 5s if not specified.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/luma/ray-3.2/video-edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ray 3.2 Video Edit below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "540p",
"duration": "5s"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/luma/ray-3.2/video-edit" \
-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/luma/ray-3.2/video-edit";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "540p",
"duration": "5s"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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 = {
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"resolution": "540p",
"duration": "5s"
}
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/luma/ray-3.2/video-edit", 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)Ray 3.2 Video Edit is a Luma model for video editing, exposed as a REST API on WaveSpeedAI. Luma Ray 3.2 Video Edit is a fast AI video-to-video editing model that re-renders an existing source video from a text prompt while preserving the original motion and timing. Ready-to-use REST inference API for video restyling, creative edits, product videos, advertising creatives, social media clips, visual storytelling, and professional video editing workflows with simple integration, no coldstarts, and 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/luma/luma-ray-3.2-video-edit.
Ray 3.2 Video Edit starts at $0.72 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`, `video`, `resolution`, `duration`, `start_image`. 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/luma/luma-ray-3.2-video-edit.
Median end-to-end generation time on WaveSpeedAI is around 385 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Luma). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.