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

firemoon/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.

Firemoon size parameter for image generation

The size parameter controls the image dimensions. Examples include 'square_hd' and 'landscape_16_9'. Alternatively, the aspectRatio parameter can be used to map aspect ratios like '16:9' to corresponding size presets (e.g., '16:9' maps to 'landscape_16_9').

Firemoon seed parameter for reproducible results

The seed parameter can be specified in generateImage() to produce reproducible results. For example: seed: 12345.

Firemoon providerOptions for custom parameters

Additional Firemoon-specific parameters can be passed through the providerOptions object under the firemoon key. Available custom parameters include lora_scale, num_images, image_size, output_format, guidance_scale, num_inference_steps, and enable_safety_checker.

Firemoon fine-tuned model example with provider options

Example of using a fine-tuned model with providerOptions: await generateImage({ model: firemoon.image('firemoon-studio/memphis-style'), prompt: 'a man smiling at the camera', size: 'landscape_16_9', providerOptions: { firemoon: { lora_scale: 0.6, num_images: 1, image_size: 'landscape_4_3', output_format: 'jpeg', guidance_scale: 3.5, num_inference_steps: 28, enable_safety_checker: true } } });

Give your agent this brain