wan2.7-r2v-nsfw API

Use the exact model ID wan2.7-r2v-nsfw. The model field must match this page exactly.

Sample outputwan2.7-r2v-nsfwPOST /v1/videos5.0s

Parameters: duration=5resolution=1080Pratio=16:9Reference image

Prompt: One continuous take, no cuts. Keep the woman, the white bikini, the tortoiseshell glasses, the striped towel and the poolside exactly as in the first frame. She pushes up off her forearms and turns slowly onto her side and then square to the lens, settling back on one hip; as she comes round she runs one hand back through her damp hair and lets it fall over one shoulder, then faces the camera front on, chin slightly up, still looking over the top of her glasses with a relaxed smile. The camera holds its low close position and eases back a little as she turns, keeping her framed from shoulders to hips. Warm midday sun stays from the left, bright bounce off the pale deck. Real weight and inertia, natural hair and fabric movement, no text.

This sample is deliberately mild. It is not the content limit of this model ID.

Request that produced this sample, with the input media URL replaced

{
  "model": "wan2.7-r2v-nsfw",
  "input": {
    "prompt": "One continuous take, no cuts. Keep the woman, the white bikini, the tortoiseshell glasses, the striped towel and the poolside exactly as in the first frame. She pushes up off her forearms and turns slowly onto her side and then square to the lens, settling back on one hip; as she comes round she runs one hand back through her damp hair and lets it fall over one shoulder, then faces the camera front on, chin slightly up, still looking over the top of her glasses with a relaxed smile. The camera holds its low close position and eases back a little as she turns, keeping her framed from shoulders to hips. Warm midday sun stays from the left, bright bounce off the pale deck. Real weight and inertia, natural hair and fabric movement, no text.",
    "media": [
      {
        "type": "reference_image",
        "url": "https://example.com/input-image.png"
      }
    ]
  },
  "parameters": {
    "duration": 5,
    "resolution": "1080P",
    "ratio": "16:9"
  }
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Create a task

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-r2v-nsfw",
    "input": {"prompt": "The subject in Image 1 walks through the street from Video 1.", "media": [{"type": "reference_image", "url": "https://example.com/reference.png"}, {"type": "reference_video", "url": "https://example.com/reference.mp4"}]},
    "parameters": {"resolution": "1080P", "ratio": "16:9", "duration": 5, "prompt_extend": false, "watermark": false}
  }'

Poll and download

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

bash

curl https://modelflare.dev/v1/videos/TASK_ID \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Request notes

Wan commonly uses input and parameters; frame-guided and reference-media modes must not be mixed.

Request parameters

Wan2.7 R2V uses reference_image / reference_video media and may attach reference_voice. Do not mix this workflow with first_frame / last_frame roles.

Field	Required	Notes
model	Yes	wan2.7-r2v-nsfw
input.prompt	Yes	Describe the scene and reference media using the documented syntax
input.media[]	Yes	At least one reference_image or reference_video
input.media[].reference_voice	No	Public WAV/MP3 URL for voice characteristics
parameters.resolution	No	720P / 1080P (default 1080P)
parameters.ratio	No	16:9 / 9:16 / 1:1 / 4:3 / 3:4 (ignored when first_frame is present)
parameters.duration	No	Use the shorter duration limit when a reference video is present
parameters.prompt_extend	No	Set false when this dedicated model contract requires it
parameters.watermark	No	Whether to add a watermark
parameters.seed	No	Optional random seed

Input and output limits

R2V requires at least one reference_image or reference_video, with at most five reference images/videos combined. One first_frame and a reference_voice may be attached; the duration limit is shorter when a reference video is present. The -nsfw model requires prompt_extend: false.

Documented workflow examples

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-r2v-nsfw",
    "input": {"prompt": "让图像主体沿视频动作自然移动", "media": [
      {"type": "reference_image", "url": "https://example.com/subject.png"},
      {"type": "reference_video", "url": "https://example.com/motion.mp4"}
    ]},
    "parameters": {"resolution": "1080P", "duration": 8, "prompt_extend": false}
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.

Variants

Model ID	Difference
wan2.7-r2v-nsfw	The model documented on this page.
wan2.7-r2v	The base model. Same endpoint, request contract, and billing unit; only the model ID changes — see its own page, and the pricing page for price and availability.