HappyOyster-1.0
Copy success!
Overview
HappyOyster Directing is an open-world model featuring real-time interaction and immersive narrative generation. It creates world environments from multimodal (text/image) inputs, enabling continuous, text-driven real-time world evolution at any moment.
Input
TextImage
Output
Video
Features
Prefix Completion
Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docsFunction Calling
Use function calling to connect large language models with external tools and systems.View docsCache
Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docsStructured Outputs
Structured Outputs help ensure the model returns a JSON string in the expected format.View docsPricing
- World Creation (No Reference Image)$0.3113Per voice
- World Creation (With Reference Image)$0.0077Per voice
- Prompt Injection$0.0154Per voice
- World Experience (480P)$0.0539Per second
- World Experience (720P)$0.0858Per second
Rate Limits
API Reference
Call APICopy success!
12345678910111213141516
curl --location 'https://maas.qwencloudapi.com/api/v2/apps/happyoyster-1.0-directing/openapi/v1/worlds' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"async": true,
"creationModel": "simple",
"eventStyle": "normal",
"prompt": "A window-side cafe. A young woman with long black hair, wearing a beige turtleneck sweater, sits sideways, resting her chin on her left hand and gazing out the glass window covered in raindrops. A steaming cup of dark coffee sits on the wooden table. Outside the window, a rainy night with warm yellow streetlights; indoors, a pendant lamp. A quiet rainy night.",
"resolution": "720p",
"inputImages": [
{
"url": "https://g-adoc.alcasset.com/media/maas_docs/sfm-cn/common/images/6a4b3c2d1e0f9fc7.png",
"referenceType": "default"
}
]
}'