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/options

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 provider configuration options

The Prodia provider supports: apiKey (string, defaults to PRODIA_TOKEN environment variable, sent as Bearer token in Authorization header), baseURL (string, defaults to https://inference.prodia.com/v2), headers (Record<string, string> for custom headers), fetch (custom fetch implementation for middleware or testing).

Prodia image size parameter

Specify image size using the size parameter in WIDTHxHEIGHT format, such as '1024x768'.

Prodia provider options for image generation

Prodia image models support the following provider options in providerOptions.prodia: width (number, 256–1920 pixels, overrides width from size parameter), height (number, 256–1920 pixels, overrides height from size parameter), steps (number, 1–4 computational iterations, more steps produce higher quality), stylePreset (string, visual theme: 3d-model, analog-film, anime, cinematic, comic-book, digital-art, enhance, fantasy-art, isometric, line-art, low-poly, neon-punk, origami, photographic, pixel-art, texture, craft-clay), loras (string array, up to 3 LoRA models), progressive (boolean, return progressive JPEG when using JPEG output).

Prodia provider options example

import { prodia, type ProdiaImageModelOptions } 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', providerOptions: { prodia: { width: 1024, height: 768, steps: 4, stylePreset: 'cinematic', } satisfies ProdiaImageModelOptions, }, });

Give your agent this brain