Intégrez le modèle d'IA seedance-2-omni-reference via la plateforme à ultra-faible latence MuAPI. Tarification flexible à l'usage, mise à l'échelle instantanée et disponibilité maximale.
Le modèle seedance-2-omni-reference, disponible sur MuAPI avec une facturation flexible à l'usage et une haute concurrence.
À propos de ce modèle
Accès programmatique au modèle seedance-2-omni-reference sur la plateforme MuAPI. Conçu pour les environnements de production avec une intégration d'API REST fluide et une haute fiabilité.
Analyse des coûts
| Fournisseur | Coût | Remarques |
|---|---|---|
| muapiapp | $0.18–$1.35/sec depending on resolution/quality | Per-second billing, scaling by resolution and quality (480p: $0.18/sec basic, $0.24/sec high; 720p: $0.21/sec basic, $0.30/sec high; 1080p: $0.4725/sec basic, $0.675/sec high; 4K: $0.945/sec basic, $1.35/sec high). Supports multi-modal references (image + video + audio) in a single request. |
| Fal.ai | $0.3024/sec (high) / $0.2419/sec (basic) | Fal.ai charges $0.3024/sec for high quality and $0.2419/sec for basic. muapiapp is roughly the same on high ($0.30/sec) and 13% cheaper on basic ($0.21/sec). |
| Replicate | $0.3024/sec (high) / $0.2419/sec (basic) | Replicate charges the same as Fal.ai — $0.3024/sec (high), $0.2419/sec (basic). muapiapp is competitive on high quality and 13% cheaper on basic. |
Per-second billing, scaling by resolution and quality (480p: $0.18/sec basic, $0.24/sec high; 720p: $0.21/sec basic, $0.30/sec high; 1080p: $0.4725/sec basic, $0.675/sec high; 4K: $0.945/sec basic, $1.35/sec high). Supports multi-modal references (image + video + audio) in a single request.
Fal.ai charges $0.3024/sec for high quality and $0.2419/sec for basic. muapiapp is roughly the same on high ($0.30/sec) and 13% cheaper on basic ($0.21/sec).
Replicate charges the same as Fal.ai — $0.3024/sec (high), $0.2419/sec (basic). muapiapp is competitive on high quality and 13% cheaper on basic.
** Les prix des concurrents sont estimés sur la base d'architectures de modèles et de niveaux d'utilisation similaires.
Schéma de configuration
| Paramètre | Taper | Description | Par défaut |
|---|---|---|---|
| invite | string | Video description. Use @image1…@image9 to reference images, @video1…@video3 for videos, @audio1…@audio3 for audio. To use a character sheet, reference it with @character:<request_id> (from a completed Seedance 2 Character generation). To use a trained Omni Reference character, reference it with @omni-character:<character_id> where character_id is the value returned by Omni Reference Train Character (e.g. char_1775422630065_4vbana). Both methods can be combined in the same prompt. Multiple characters are supported. Example: '@omni-character:char_1775422630065_4vbana walking through a neon-lit city at night'. | @image1 is the main character reference. A person walking on the beach at sunset, cinematic lighting |
| Résolution | Énumération (options 4) | Output resolution. Choose 480p, 720p, 1080p, or 4k; price scales with the resolution chosen. | 720p |
| URL des images | array | 9 URL des images (JPEG/PNG/WebP) . N imageprompt @imageN. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-omni-reference.png |
| URL de référence vidéo | array | 3 URL vidéo (MP4, 15). N vidéoinvite @videoN. | undefined |
| URL de référence audio | array | Up to 3 reference audio clip URLs (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt. | undefined |
| rapport hauteur/largeur | Énumération (options 6) | rapport d’aspect vidéo de sortie. | 16:9 |
| Qualité | Énumération (options 2) | Generation quality. 'high' uses the standard model ($0.30/sec output + $0.09/sec per input video second). 'basic' uses the fast model (~2x speed, $0.21/sec output + $0.063/sec per input video second). Video reference inputs incur an additional 30% surcharge based on their combined duration. | high |
| Durée (secondes) | int | Video duration in seconds (4–15). | 5 |
Video description. Use @image1…@image9 to reference images, @video1…@video3 for videos, @audio1…@audio3 for audio. To use a character sheet, reference it with @character:<request_id> (from a completed Seedance 2 Character generation). To use a trained Omni Reference character, reference it with @omni-character:<character_id> where character_id is the value returned by Omni Reference Train Character (e.g. char_1775422630065_4vbana). Both methods can be combined in the same prompt. Multiple characters are supported. Example: '@omni-character:char_1775422630065_4vbana walking through a neon-lit city at night'.
@image1 is the main character reference. A person walking on the beach at sunset, cinematic lightingOutput resolution. Choose 480p, 720p, 1080p, or 4k; price scales with the resolution chosen.
720p9 URL des images (JPEG/PNG/WebP) . N imageprompt @imageN.
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-omni-reference.png3 URL vidéo (MP4, 15). N vidéoinvite @videoN.
undefinedUp to 3 reference audio clip URLs (MP3/WAV, total max 15s). Each Nth audio corresponds to @audioN in the prompt.
undefinedrapport d’aspect vidéo de sortie.
16:9Generation quality. 'high' uses the standard model ($0.30/sec output + $0.09/sec per input video second). 'basic' uses the fast model (~2x speed, $0.21/sec output + $0.063/sec per input video second). Video reference inputs incur an additional 30% surcharge based on their combined duration.
highVideo duration in seconds (4–15).
5Documentation du développeur
Envoyez une requête POST au point de terminaison du modèle avec votre clé MuAPI dans l'en-tête et les paramètres requis dans le corps JSON.
Foire aux questions