Video Model Swap API

Another person in the same video: send the clip and a photo of the new model, get the clip back with that person wearing the outfit, same movement and setting.

Get an API key Claude MCP

POST/v1/generateworkflow: swap_video_model-v1

One endpoint serves every workflow — this page documents swap_video_model-v1, the current version. Credits are debited at submission (2.8 cr/s standard, 3.7 cr/s pro); a failed generation is refunded automatically. Earlier versions of this endpoint, if any, keep being served under their own names. This workflow needs an active plan.

Parameter	Value for this workflow
workflow	"swap_video_model-v1" required
source_video	Your video — one public HTTPS URL.required
model_image	New model (photo) — one public HTTPS URL.required
duration	per engine (seconds)
tier	"standard" (2.8 cr/s) or "pro" (3.7 cr/s)
webhook_url	Optional — we POST the outcome here when the generation settles. Without it, poll the URL returned in the response until the status settles.

Example request

curl -X POST https://thenewblack.ai/api/v1/generate \
  -H "Authorization: Bearer tnb_live_XXXXXXXXXXXX" \
  -H "Content-Type: application/json" \
  -d '{
    "workflow": "swap_video_model-v1",
    "source_video": "https://example.com/clip.mp4",
    "model_image": "https://example.com/model.jpg",
    "tier": "standard"
  }'

// 202 Accepted
{
  "generation_id": "3f1c9a6e-...",
  "status": "running",
  "poll": "/api/v1/generations/3f1c9a6e-..."
}

Example response

Poll /v1/generations/{id} (or receive the webhook) until the generation settles:

// 200 OK
{
  "generation_id": "3f1c9a6e-...",
  "workflow": "swap_video_model",
  "status": "succeeded",
  "result": {
    "type": "video",
    "url": "https://.../result.mp4",
    "thumbnail": "https://.../thumb.webp"
  }
}

Results are stored for 48 hours — copy them to your own storage. Authentication, errors and webhooks are documented in the full API reference.

Frequently asked questions

What are the two inputs?

The video first, then a photo of the new model — front on, face visible. The face, hair and skin become the new model's; everything else stays.

How is it billed?

By the second of the video you send, standard or pro. The length is read from the file before the job starts.

How much does it cost?

2.8 credits per second on the standard tier, 3.7 per second on pro. Credits come with plans and packs; a failed generation is always refunded.

Other endpoints: Virtual Try-On API · AI Fashion Models API · Fashion Design API · Reimagine Model API · Swap Model API · AI Stylist API · all endpoints