本页还没有译文
本页 8 段还没译成日本語,下面显示的是英文原文。wrapImageModel
还没翻译译自英文(ai-sdk.dev)本页 8 段都还没译
The wrapImageModel function provides a way to enhance the behavior of image models
by wrapping them with middleware.
import { generateImage, wrapImageModel } from 'ai';
import { openai } from '@ai-sdk/openai';
const model = wrapImageModel({
model: openai.image('gpt-image-2.5-sunburst'),
middleware: yourImageModelMiddleware,
});
const { image } = await generateImage({
model,
prompt: 'Santa Claus driving a Cadillac',
});Import
import { wrapImageModel } from "ai"API Signature
Parameters
model(ImageModelV4): The original ImageModelV4 instance to be wrapped.middleware(ImageModelV4Middleware | ImageModelV4Middleware[]): The middleware to be applied to the image model. When multiple middlewares are provided, the first middleware will transform the input first, and the last middleware will be wrapped directly around the model.modelId(string): Optional custom model ID to override the original model's ID.providerId(string): Optional custom provider ID to override the original model's provider.
Returns
A new ImageModelV4 instance with middleware applied. The wrapped model
preserves the original model's supportsFileInputs and supportsMaskInputs
capabilities by default. Middleware can override them with
overrideSupportsFileInputs and overrideSupportsMaskInputs. Returning
undefined from an override intentionally marks that capability as unknown.
const model = wrapImageModel({
model: originalModel,
middleware: {
specificationVersion: 'v4',
overrideSupportsFileInputs: () => true,
overrideSupportsMaskInputs: () => false,
},
});AI 翻译查看英文原文