MuseMachine

A modular AE-GAN pipeline for portrait generation.

Architecture

Component	Description
Encoder	VAE encoder producing latent representations
Generator	Decodes latent vectors into coarse images
Refiner	Iteratively refines generations over 4 steps
Discriminator	PatchGAN-style discriminator

Hyperparameters

{
  "image_size": 256,
  "latent_dim": 256,
  "batch_size": 4,
  "epochs": 300,
  "lr_g": 0.0002,
  "lr_d": 5e-05,
  "alpha_recon": 100.0,
  "beta_adv": 1.0,
  "beta_kl": 0.05,
  "noise_std": 0.15,
  "refinement_steps": 4,
  "refiner_step_size": 0.08,
  "refine_decay": 0.8,
  "dataset_name": "ajehsmihba/aesthetic-female-portraits",
  "outputs_dir": "outputs",
  "models_dir": "models",
  "save_every": 50,
  "push_to_hf": true,
  "hf_repo_id": "ajehsmihba/MuseMachine",
  "grad_clip": 1.0,
  "vis_every": 10
}

Best Metrics

{
  "D": 0.8508812636137009,
  "EG": 37.70127280553182,
  "KL": 160.19142532348633,
  "Recon": 0.060111300088465214,
  "Coarse_Recon": 0.0729169634481271
}

Resume Training

from huggingface_hub import hf_hub_download
import torch

ckpt_path = hf_hub_download(repo_id="ajehsmihba/MuseMachine", filename="best_checkpoint.pth")
ckpt = torch.load(ckpt_path, map_location="cpu")