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

luma/options

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

Luma provider configuration options

Luma provider supports these configuration options: apiKey (string, defaults to LUMA_API_KEY environment variable), baseURL (string, defaults to https://api.lumalabs.ai), headers (Record<string,string> for custom headers), and fetch (custom fetch implementation for middleware or testing).

Luma image generation provider options

Luma image generation supports these provider-specific options: maxImagesPerCall (number, defaults to 1, overrides maximum number of images generated per API call), pollIntervalMillis (number, defaults to 500ms, controls how frequently the API is checked for completed images), and maxPollAttempts (number, defaults to 120, limits how long to wait for results before timing out).

Luma image generation with custom settings example

Example of generating an image with custom Luma provider options: `const { image } = await generateImage({ model: luma.image('photon-1'), prompt: 'A serene mountain landscape at sunset', aspectRatio: '16:9', maxImagesPerCall: 1, providerOptions: { luma: { pollIntervalMillis: 5000, maxPollAttempts: 10 } } });`

Give your agent this brain