{
  "architecture": "latent-diffusion-dit",
  "objective": "rectified-flow",
  "dit": {
    "dim": 384,
    "depth": 12,
    "heads": 6,
    "patch": 2,
    "latent_ch": 4,
    "latent_size": 32,
    "text_dim": 512,
    "mlp_ratio": 4.0
  },
  "vae": "stabilityai/sd-vae-ft-mse",
  "text_encoder": "openai/clip-vit-base-patch32",
  "max_tokens": 40,
  "resolution": 256,
  "trainable_parameters": 40013980,
  "vae_parameters": 83653863,
  "text_encoder_parameters": 63165952,
  "total_parameters_incl_frozen": 186833795,
  "training": {
    "steps": 120000,
    "batch_size": 256,
    "pairs": 2986571,
    "val_pairs": 4096,
    "optimizer": "adamw",
    "lr": 0.0002,
    "betas": [
      0.9,
      0.99
    ],
    "warmup": 1000,
    "ema": 0.9999,
    "cfg_dropout": 0.1,
    "best_val_loss": 0.7852968573570251,
    "dataset": "undefined443/cc12m-wds-coco-recaptioned"
  },
  "sampling": {
    "steps": 50,
    "cfg": 5.0
  },
  "eval": {
    "fid": 34.06,
    "clip_score": 29.27,
    "n": 5000,
    "cfg": 5.0,
    "dataset": "MS-COCO val2014, 256 center crop",
    "protocol": "torchmetrics FrechetInceptionDistance + CLIPScore (openai/clip-vit-base-patch32)",
    "real_image_clip_score": 30.05
  }
}