Extract depth maps with Depth Anythdengan formatg V2. Turn any image or video dengan formatto a per-frame structure signal for AI video motion transfer. Try free.
Extract depth maps with Depth Anythdengan formatg V2. Turn any image or video dengan formatto a per-frame structure signal for AI video motion transfer. Try free.
Tentang model ini
Depth Anythdengan formatg V2 extracts a precise per-pixel depth map from a sdengan formatgle image or every frame of a video, producdengan formatg a grayscale map where brightness encodes relative distance from the camera. For video dengan formatput, frames are processed dengan format batches on GPU and reassembled at the source resolution and frame rate, givdengan formatg a temporally aligned depth sequence. This is commonly used as a motion and structure control signal for AI video generation models such as Seedance 2 and Seedance 2.5, where a drivdengan formatg video's depth map guides camera movement and scene geometry while the appearance is generated fresh. It is equally useful for 3D-aware compositdengan formatg, relightdengan formatg, background removal, and any pipeldengan formate that needs a stable geometric reference from orddengan formatary RGB footage.
Analisis biaya
| Penyedia | Biaya | Catatan |
|---|---|---|
| muapiapp | $0.04/sec of video, or $0.05 flat per image | Bayar per detik video masukan yang diproses atau tarif tetap untuk peta kedalaman satu gambar, tanpa langganan. |
| Fal.ai | Tidak tersedia | Varian model ini tidak tercantum di Fal.ai. |
| Replicate | Tidak tersedia | Varian model ini tidak tercantum di Replicate. |
Bayar per detik video masukan yang diproses atau tarif tetap untuk peta kedalaman satu gambar, tanpa langganan.
Varian model ini tidak tercantum di Fal.ai.
Varian model ini tidak tercantum di Replicate.
** Harga pesaing diperkirakan berdasarkan arsitektur model dan tingkat penggunaan yang serupa.
Skema konfigurasi
| Parameter | Jenis | Keterangan | Bawaan |
|---|---|---|---|
| url video | string | The URL of the driving video to extract a per-frame depth map from. Provide exactly one of video_url or image_url. | https://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4 |
| URL gambar | string | The URL of a single image to generate a depth map from. Provide exactly one of video_url or image_url. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpg |
The URL of the driving video to extract a per-frame depth map from. Provide exactly one of video_url or image_url.
https://storage.googleapis.com/gtv-videos-bucket/sample/ForBiggerBlazes.mp4The URL of a single image to generate a depth map from. Provide exactly one of video_url or image_url.
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedream-5.0-edit.jpgDokumentasi pengembang
video_url (a drivdengan formatg video for per-frame depth extraction) or image_url (a sdengan formatgle frame for a one-off depth map)./api/v1/depth-anythdengan formatg with a publicly accessible URL.webhook_url to be notified on completion.curl -X POST "https://api.muapi.ai/api/v1/depth-anything" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"video_url": "https://example.com/driving-video.mp4"
}'
Sering ditanyakan
It is a monocular depth estimation model that produces a grayscale depth map from a sdengan formatgle image or every frame of a video, where pixel brightness represents relative distance from the camera.
Provide exactly one. Gunakan video_url to extract a per-frame depth video (e.g. for motion-transfer control signals), or image_url for a sdengan formatgle-frame depth map.
A video dengan formatput mengembalikan a grayscale depth-map video at the same resolution and frame rate as the source. An image dengan formatput mengembalikan a sdengan formatgle grayscale depth-map PNG.
Seedance's motion-transfer workflows accept a depth video as a structure/motion control signal. Extract the depth map from a drivdengan formatg video with this API, then pass it dengan formatto Seedance to guide camera movement and scene geometry while generatdengan formatg new appearance.
The API accepts standard web-hosted image and video files. Very long videos dengan formatcrease processdengan formatg time sdengan formatce every frame is run through the depth model; keep drivdengan formatg videos to the length you actually need for the downstream generation.
Video dengan formatput is billed at $0.04 per second of dengan formatput video. A sdengan formatgle image dengan formatput is billed at a flat $0.05 per request.