VOID Video Inpainting removes objects from videos using mask-guided inpainting. Supports quad-mask or auto-generated SAM-3 masks, optional Pass 2 refinement for temporal consistency, adjustable denoising steps, guidance scale, and temporal window size. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Siap
$0.05per run·~20 / $1
The man is having breakfast.
VOID Video Inpainting removes objects or people from video footage and fills the background with realistic, temporally consistent content. Describe what to remove and what the background should look like — the model handles the rest, with optional mask video input for precise control.
Text-driven object removal Describe the object or person to remove in plain language — no manual masking required. The model uses SAM-3 to auto-generate a mask from your text description.
Custom mask video support Upload a pre-prepared VOID-style quadmask or simple binary mask video for precise, frame-accurate removal control.
Background inpainting Describe the desired background after removal — the model fills the gap with contextually appropriate, motion-consistent content.
Pass 2 refinement Enable enable_pass2_refinement for additional warped-noise refinement that improves temporal consistency on longer clips.
Fine-grained generation control Adjust inference steps, guidance scale, denoising strength, and temporal window size for precise output control.
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Input video containing the object to remove (URL). |
| prompt | Yes | Text description of the desired background after object removal. |
| mask_video | No | Mask video URL. Supports VOID quadmask (4 grayscale values) or simple binary mask. Auto-generated if omitted. |
| mask_prompt | No | Text description of what to mask/remove. Used to auto-generate a mask when mask_video is not provided. |
| enable_pass2_refinement | No | Run Pass 2 warped-noise refinement for improved temporal consistency. Slower but higher quality. Default: false. |
| negative_prompt | No | Negative prompt to guide generation away from undesired outputs. |
| num_inference_steps | No | Number of denoising steps. Range: 1–50. Default: 30. Higher = better quality, slower. |
| guidance_scale | No | Classifier-free guidance scale. Range: 0–20. Default: 1. |
| strength | No | Denoising strength. Range: 0–1. Default: 1 (full denoising). |
| num_frames | No | Temporal window size. Valid values: 69, 77, 85, …, 197. Default: 85. |
| seed | No | Random seed for reproducible results. |
The mask_video supports two formats:
If mask_video is not provided, a mask is auto-generated from mask_prompt using SAM-3.
| Pass 2 Refinement | Mask Video | Cost |
|---|---|---|
| No | No (auto) | $0.05 |
| Yes | No (auto) | $0.10 |
| No | Yes | $0.10 |
| Yes | Yes | $0.15 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/void-video-inpainting/mask with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Void Video Inpainting Mask below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"enable_pass2_refinement": false,
"num_inference_steps": 30,
"guidance_scale": 1,
"strength": 1,
"num_frames": 85
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/void-video-inpainting/mask" \
-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/wavespeed-ai/void-video-inpainting/mask";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"enable_pass2_refinement": false,
"num_inference_steps": 30,
"guidance_scale": 1,
"strength": 1,
"num_frames": 85
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"enable_pass2_refinement": False,
"num_inference_steps": 30,
"guidance_scale": 1,
"strength": 1,
"num_frames": 85
}
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/wavespeed-ai/void-video-inpainting/mask", 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)Void Video Inpainting Mask is a WaveSpeedAI model for video editing, exposed as a REST API on WaveSpeedAI. VOID Video Inpainting removes objects from videos using mask-guided inpainting. Supports quad-mask or auto-generated SAM-3 masks, optional Pass 2 refinement for temporal consistency, adjustable denoising steps, guidance scale, and temporal window size. 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/wavespeed-ai/void-video-inpainting-mask.
Void Video Inpainting Mask starts at $0.050 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`, `seed`, `guidance_scale`, `num_inference_steps`, `negative_prompt`. 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/wavespeed-ai/void-video-inpainting-mask.
Average end-to-end generation time on WaveSpeedAI is around 378 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.