Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Wanx design images

Wanx Creative Poster v1

Text-to-poster generation with typography, backgrounds, style presets and follow-up resolution enhancement. Published access is a finite free trial.

restrictedClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
30 of 38 specification fields collected
Text input limitTitle ≤30; subtitle ≤30; body ≤50; Chinese + English prompts ≤50 combined. Separate fields, not one context window.See specification notes below
Maximum outputNot collectedAwaiting source review
Input billingSee billing notesAlibaba Model Studio · Beijing · trial only
Output billingSee billing notesAccess and billing notes below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Streaming
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
API aliases
wanx-poster-generation-v1Source for API aliases (opens in a new tab)
Published availability regions
China (Beijing)Source for Published availability regions (opens in a new tab)
Request mode
Async HTTP submission with X-DashScope-Async: enable, followed by task-status queries. This is not Batch API support.Source for Request mode (opens in a new tab)
Published price
Trial only; paid usage unavailable.Source for Published price (opens in a new tab)
Usage metering
500 generated images in the published trial; requests stop when allowance is exhausted.Source for Usage metering (opens in a new tab)
Free usage allowance
500 images; 90 days from the latest activation, model release or application approval. Account eligibility is unverified.Source for Free usage allowance (opens in a new tab)
Required request fields
Title and at least one of prompt_text_zh or prompt_text_en for generation; parameters is an empty object. Enhancements reuse returned auxiliary_parameters.Source for Required request fields (opens in a new tab)
Maximum prompt characters
Title ≤30; subtitle ≤30; body ≤50; Chinese + English prompts ≤50 combined. Separate fields, not one context window.Source for Maximum prompt characters (opens in a new tab)
Images per request
generate: 1–4, default 1; values above 4 are capped at 4. sr/hrf: one selected image.Source for Images per request (opens in a new tab)
Generation modes
generate: poster and enhancement metadata, sr: resolution enhancement, hrf: high-definition restorationSource for Generation modes (opens in a new tab)
Poster enhancement workflow
Choose one generated poster and pass its corresponding auxiliary_parameters into sr or hrf, preserving the other inputs. The service cannot change existing title, body or style; changed content requires new generation.Source for Poster enhancement workflow (opens in a new tab)
Poster styles
View all 18 entries
  • 2D Illustration 1
  • 2D Illustration 2
  • Vast Nebula
  • Rich Colors
  • Light Particles
  • Transparent Glass
  • Paper-cutting Art
  • Origami Art
  • Chinese Ink Wash
  • Chinese Embroidery
  • Realistic Scene
  • 2D Cartoon
  • Children’s Watercolor
  • Cyber Background
  • Light Blue Abstract
  • Dark Blue Abstract
  • Abstract Dots and Lines
  • Fairy Tale Oil Painting
Source for Poster styles (opens in a new tab)

Named lora_name controls of this API, not independently documented model checkpoints. Localized style labels may differ between language versions.

Generation controls
Horizontal layout by default or Vertical. lora_weight: 0–1, default 0.8. ctrl_ratio: 0–1, default 0.7. ctrl_step: above 0 through 1, default 0.7. creative_title_layout=false by default.Source for Generation controls (opens in a new tab)
Generated assets
render_urls: poster with text, bg_urls: background without text, auxiliary_parameters: one enhancement token per posterSource for Generated assets (opens in a new tab)
Output link expiry
Poster URLs, background URLs and auxiliary parameters expire after 24 hours. This is not a complete data-retention policy.Source for Output link expiry (opens in a new tab)
Output filtering
A blocked result may contain a moderation message instead of an image URL. Callers must not assume every returned list item is a URL.Source for Output filtering (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Alibaba Model Studio · Beijing · trial only

Provider source (opens in a new tab)
API model ID
wanx-poster-generation-v1
Access
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis. Async HTTP submission with X-DashScope-Async: enable, followed by task-status queries. This is not Batch API support. Finite trial only.
Regions
China (Beijing)
Published request quota
120 requests per minuteSource for Published request quota (opens in a new tab)
Task submission rate
2 submissions per secondSource for Task submission rate (opens in a new tab)
Quota scope
Per-model limits shared by the Alibaba Cloud account and RAM usersSource for Quota scope (opens in a new tab)
Free usage allowance
500 images; 90 days from the latest activation, model release or application approval. Account eligibility is unverified.Source for Free usage allowance (opens in a new tab)
Request mode
Async HTTP submission with X-DashScope-Async: enable, followed by task-status queries. This is not Batch API support.Source for Request mode (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Result-link expiry is documented. Input retention, training use and account entitlement are not verified.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Classification inference: separately named native Alibaba hosted release; reviewed official model cards and APIs describe service access but do not provide model weights. No exact released checkpoint is identified by those sources. Public Wan checkpoints, style controls and research architectures are not assumed equivalent.

Classification evidence (opens in a new tab)

Lifecycle dates

Model Studio release21 Jun 2024Source (opens in a new tab)

Sources reviewed