new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

replicate/options

5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Replicate provider customization options

The Replicate provider supports the following optional settings: baseURL (string, default `https://api.replicate.com/v1`), apiToken (string, defaults to `REPLICATE_API_TOKEN` environment variable), headers (Record<string,string>), and fetch (custom fetch implementation).

Replicate model-specific options example

Example of passing provider options to Replicate image models: ```ts import { replicate, type ReplicateImageModelOptions } from '@ai-sdk/replicate'; import { generateImage } from 'ai'; const { image } = await generateImage({ model: replicate.image('recraft-ai/recraft-v3'), prompt: 'The Loch Ness Monster getting a manicure', size: '1365x1024', providerOptions: { replicate: { style: 'realistic_image', } satisfies ReplicateImageModelOptions, }, }); ```

Replicate provider options for image generation

Common provider options for Replicate image generation: maxWaitTimeInSeconds (number, default 60 seconds for sync mode), guidance_scale (number for classifier-free guidance), num_inference_steps (number, more steps = higher quality but slower), negative_prompt (string), output_format ('png' | 'jpg' | 'webp'), output_quality (number 1-100, applies to jpg and webp), strength (number 0-1, for img2img transformations).

Replicate sync mode prediction timeout

Replicate uses sync mode by default with a 60-second timeout for predictions. The maxWaitTimeInSeconds option can be set to a positive number to use a custom duration (e.g., 120 for 2 minutes).

Replicate model parameter variations

Different Replicate models have different parameter names and capabilities. Model support for size and other parameters varies by model. Check the model's documentation on Replicate for supported options and additional parameters that can be passed via providerOptions.replicate.

Give your agent this brain