Aller au contenu

AlibabaImage modelVérification

Wan 2.5 Preview API

Model IDwan-2-5-preview-image-to-image

Wan 2.5 Preview for image generation, image editing and audio-synchronized video.

  • Image to image
  • Text to image
  • Image to video
  • Text to video
  • Up to 3 input images
  • Up to 10 seconds
  • 480p, 720p or 1080p output

Lancez Wan 2.5 Preview dans le playground

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

Paramètres

Modèle
model

Wan 2.5 PreviewImage to imagewan-2-5-preview-image-to-image

Obligatoire
input.prompt

Positive prompt describing the desired image editing operation. ≤ 2000 chars

input.imageUrls

Input images (1-3) ≤ 3 items · HTTPS image URL or media:<uuid>

input.n

Number of images to generate (1-4), directly affects pricing. 1–4

Options courantes
input.size

Output image resolution.Output image resolution. If size is not specified, the system will generate an image with a total pixel size of 1280×1280 by default, and maintain the aspect ratio (approximate value) according to the following rules: For single-image input: the aspect ratio is consistent with the input image. For multi-image input: the aspect ratio is consistent with the last input image.

Avancé (3)
input.negativePrompt

Negative prompt describing unwanted content. ≤ 500 chars

input.promptExtend

Enable intelligent prompt extension.

input.seed

Random seed for reproducible generation. -1–2147483647

Estimated cost
Chargement du prix…

Les crédits sont réservés à l’acceptation d’une tâche et débités seulement en cas de succès. Une tâche échouée libère la réservation ; un résultat non confirmé reste réservé jusqu’à vérification.

Aperçu de la requête

{"model": "wan-2-5-preview-image-to-image","input": {"n": 1,"promptExtend": true}}

Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.

Résultat

Run the request and the result appears here, with its status and cost.

Tarifs de Wan 2.5 Preview

Prices are shown in USD for each available variant and specification. The billing unit is shown with its rate; an official reference appears only when a matching list price is published.

Chargement du prix…
  • Charged only on successOnly successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
  • Safe retriesLes nouvelles tentatives idempotentes avec la même clé ne créent pas de second débit.
  • Price changesEnvoyez expectedPriceMicros pour rejeter la tâche avec PRICE_CHANGED si le prix a changé après son affichage.

Comparez les variantes de Wan 2.5 Preview

Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.

  • Image to image

    wan-2-5-preview-image-to-image

    Image to image; Texte, image

  • Text to imagePar défaut

    wan-2-5-preview-text-to-image

    Text to image; Texte

  • Image to video

    wan-2-5-preview-image-to-video

    Image to video; Texte, image, audio; 5–10 s; 480p, 720p, 1080p

  • Text to video

    wan-2-5-preview-text-to-video

    Text to video; Texte, audio; 5–10 s

Ce que Wan 2.5 Preview sait faire

Alibaba describes Wan 2.5 Preview as four model tasks: text-to-image, image editing, text-to-video and image-to-video. It highlights synchronized audio for the video models and visual text and instruction following for image generation. These are manufacturer descriptions; assess output quality for your prompts.

The Hermes catalog lists all four task types. Image editing accepts up to three image references; both video variants list an audioUrl input. Their size, duration and resolution fields differ, so select the exact task and check its current status and price.

Capacités

  • Up to 10 seconds

    Choose a length from 5 to 10 seconds.

    duration

    Variantes: Image to video, Text to video

  • 480p, 720p or 1080p output

    Pick the output resolution: 480p, 720p or 1080p.

    resolution

    Variantes: Image to video

  • Up to 3 input images

    Send up to 3 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    Variantes: Image to image

  • Up to 4 images per request

    Ask for several results in one task.

    n

    Variantes: Image to image, Text to image

  • Audio input

    Accepts reference audio as input.

    audioUrl

    Variantes: Image to video, Text to video

  • Negative prompt

    Describe what to keep out of the result.

    negativePrompt

    Every variant

  • Seed

    Accepts a seed value.

    seed

    Every variant

Cas d’usage

  1. Create and edit images

    Start from text or supply references to the image-editing variant.

  2. Make video with an audio reference

    Use an appropriate video variant and its listed audio input.

  3. Explore visual concepts

    Compare image results for layouts, illustrations or text-bearing graphics.

Appelez Wan 2.5 Preview depuis votre code

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    Créez une clé d’API

    In the dashboard, with the jobs:create and jobs:read scopes. Clés d’API
  2. 2

    Soumettre une tâche

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

Requête minimale

Required fields only, generated from the schema of Image to image. Set HERMES_API_KEY in your environment.

Model ID
wan-2-5-preview-image-to-image
Point de terminaison
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "wan-2-5-preview-image-to-image",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "imageUrls": [
      "https://example.com/input.png"
    ],
    "n": 1
  }
}'

# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
  -H "Authorization: Bearer $HERMES_API_KEY"

Paramètres d’entrée

Fields of Image to image (wan-2-5-preview-image-to-image). Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.

ChampTypeObligatoirePar défautValeurs autorisées et contraintes
prompt
stringobligatoire—

Positive prompt describing the desired image editing operation.

≤ 2000 chars

imageUrls
string[]obligatoire—

Input images (1-3)

≤ 3 items, HTTPS image URL or media:<uuid>

negativePrompt
stringfacultatif—

Negative prompt describing unwanted content.

≤ 500 chars

size
stringfacultatif—

Output image resolution.Output image resolution. If size is not specified, the system will generate an image with a total pixel size of 1280×1280 by default, and maintain the aspect ratio (approximate value) according to the following rules: For single-image input: the aspect ratio is consistent with the input image. For multi-image input: the aspect ratio is consistent with the last input image.

Parmi: "1280*1280", "1024*1024", "800*1200", "1200*800", "960*1280", "1280*960", "720*1280", "1280*720", "1344*576"

n
integerobligatoire1

Number of images to generate (1-4), directly affects pricing.

1–4

promptExtend
booleanfacultatiftrue

Enable intelligent prompt extension.

seed
integerfacultatif—

Random seed for reproducible generation.

-1–2147483647

Importez d’abord un fichier local

Remplacez l’URL d’exemple par la référence média renvoyée.

POST /api/v1/media
curl -X POST https://api.hermes-ai.net/api/v1/media \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: image/png" \
  --data-binary @input.png
# → { "reference": "media:<uuid>", ... }  Use the reference in an image, video or audio field.
Headers, response, task statuses and errors
En-têteValeurRemarques
AuthorizationBearer <API key>Ou envoyez la clé dans x-api-key.
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>Obligatoire. Ne le réutilisez que pour retenter la même requête.
ChampTypeRemarques
idstringID de tâche Hermes AI. Utilisez-le pour interroger.
modelstringSlug du modèle.
statusstringVoir les statuts de tâche.
errorCodestring | nullDéfini lorsqu’une tâche échoue ou doit être examinée.
priceMicrosintegerDevis fixé à l’admission, en micro-unités USD.
currency"USD"
createdAt / updatedAtstringHorodatages ISO 8601.
assets[]array{ id, type, url?, text? }. url est un lien /api/v1/results/<uuid> de même origine.
replayedbooleanSoumission uniquement. true lorsqu’une nouvelle tentative idempotente correspond.
StatutFinalSignification
queuednonAcceptée, en attente d’un worker.
submittingnonEn cours d’envoi au fournisseur du modèle.
runningnonLe modèle est en cours de génération.
succeededouiTerminée. Les résultats sont dans assets.
failedouiTerminée sans résultat. La réservation est libérée.
reconciliation_requiredouiThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPCodeSignification et action
401AUTH_REQUIREDClé d’API ou session manquante ou invalide.
403INSUFFICIENT_SCOPELa clé d’API n’a pas la portée requise par ce point de terminaison.
403PERMISSION_DENIEDCet identifiant ne peut pas effectuer cette opération.
429API_KEY_RATE_LIMITEDLa limite de débit de la clé d’API est atteinte. Respectez Retry-After.
429API_KEY_USAGE_EXCEEDEDLa clé d’API a atteint sa limite d’utilisation. Créez une nouvelle clé.
400INVALID_REQUESTLe corps n’est pas un objet JSON ou une valeur obligatoire manque.
400INVALID_IDEMPOTENCY_KEYIdempotency-Key doit comporter de 1 à 128 caractères ASCII imprimables.
400INVALID_MODEL_INPUTinput ne correspond pas au schéma du modèle (champ inconnu, champ obligatoire manquant ou valeur invalide).
400 / 413INPUT_TOO_LARGELe corps de la requête dépasse 256 Ko. Importez d’abord les médias et envoyez une référence média.
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDAucun modèle n’a ce slug.
404JOB_NOT_FOUNDAucune tâche avec cet ID n’appartient à votre compte.
409IDEMPOTENCY_CONFLICTCette Idempotency-Key a été utilisée avec une autre entrée. Utilisez une nouvelle clé pour une nouvelle requête.
409PRICE_CHANGEDLe prix diffère de expectedPriceMicros. Récupérez le prix et confirmez à nouveau.
409MODEL_PRICE_UNAVAILABLEAucun prix n’est encore configuré pour ce modèle ; il ne peut donc pas s’exécuter.
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITSLes crédits disponibles ne couvrent pas le prix de la tâche.
429RATE_LIMITEDTrop de soumissions de tâches par minute. Réessayez plus tard.
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITEDTrop de tâches inachevées. Attendez qu’une tâche se termine.
503EXECUTION_UNAVAILABLEL’exécution n’est pas configurée pour ce modèle actuellement.
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDEDThis model is temporarily unavailable. Try again later.
503EXECUTION_TEMPORARILY_UNAVAILABLEL’exécution est temporairement indisponible. Réessayez avec la même Idempotency-Key.
503AUTH_UNAVAILABLEL’authentification est temporairement indisponible. Réessayez plus tard.
503API_UNAVAILABLEL’API est temporairement indisponible. Réessayez plus tard.

FAQ de l’API Wan 2.5 Preview

Answers built from the model's schema and the Hermes AI API contract.

Do all Wan 2.5 tasks take the same inputs?

No. Image and video variants have separate schemas; the video tasks list an audio field, while image editing lists image references.

What can the Wan 2.5 Preview API do?

Wan 2.5 Preview by Alibaba handles image vers image, texte vers image, image vers vidéo et la texte vers vidéo. The catalog lists 4 variants, each with its own model ID and input schema. Check the current availability before sending a request.

Which durations, resolutions and aspect ratios does Wan 2.5 Preview support?

Across its variants, Wan 2.5 Preview supports durations from 5 to 10 seconds et la 480p, 720p et la 1080p resolution. Each variant accepts its own subset; the variants table on this page lists them.

What input does Wan 2.5 Preview accept?

A text prompt of up to 2,000 characters, plus image ou audio input (up to 3 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.

How is Wan 2.5 Preview priced and billed?

You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.

Which Wan 2.5 Preview variant should I choose?

For image to image, use Image to image; for text to image, use Text to image; for image to video, use Image to video; for text to video, use Text to video. Pick the task first, then compare the tiers in the variants table.

How do I call the Wan 2.5 Preview API from code?

Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.

Can I try Wan 2.5 Preview without writing code?

Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.

What happens when a task fails or I hit a rate limit?

A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.