Views
No views yet
neural-art repository code. It generates images conditioned on Emotiv Epoch X style
EEG input.generative/checkpoints/checkpoint.pth: fine-tuned latent diffusion checkpoint.generative/checkpoints/checkpoint-eeg.pth: EEG encoder checkpoint required by the
current inference code.config15.yaml: model architecture configuration.generative/: custom model code copied from src/generation-service/generative.inference.py: small helper for loading the model from this Hub repository.transformers or diffusers pipeline.
Install the runtime dependencies, clone this repository, and run inference from the
repository root.pip install -r requirements.txt1import torch
2from inference import NeuralArtPipeline
3
4pipe = NeuralArtPipeline(device="cuda" if torch.cuda.is_available() else "cpu")
5
6# EEG input should match the training/inference shape used by the original repo:
7# a 2D tensor/array with shape [channels, time].
8eeg = torch.randn(14, 1024)
9images = pipe(eeg, num_samples=2, ddim_steps=100)
10
11for i, image in enumerate(images):
12 image.save(f"sample_{i}.png")neural-art