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

prodia/capabilities

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

Prodia image model factory

Create Prodia image models using the .image() factory method.

Prodia image generation basic example

import { writeFileSync } from 'node:fs'; import { prodia } from '@ai-sdk/prodia'; import { generateImage } from 'ai'; const { image } = await generateImage({ model: prodia.image('inference.flux-fast.schnell.txt2img.v2'), prompt: 'A cat wearing an intricate robe', }); const filename = `image-${Date.now()}.png`; writeFileSync(filename, image.uint8Array); console.log(`Image saved to ${filename}`);

Prodia seed parameter for reproducibility

Use the seed parameter in generateImage to get reproducible results. Pass an integer value such as seed: 12345.

Prodia provider metadata in response

The generateImage response includes provider-specific metadata in providerMetadata.prodia.images[]. Each image object may contain: jobId (string, unique identifier for generation job), seed (number, seed used for generation), elapsed (number, generation time in seconds), iterationsPerSecond (number, processing speed metric), createdAt (string, timestamp when job was created), updatedAt (string, timestamp when job was last updated).

Give your agent this brain