config.json

{
  "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,
  "trainable_parameters": 40013980,
  "total_parameters_incl_frozen": 161500000,
  "sampling": {
    "steps": 50,
    "cfg": 6.0
  },
  "eval": {
    "fid": 39.54,
    "clip_score": 28.04,
    "n": 5000,
    "dataset": "MS-COCO val2014, 256 center crop",
    "protocol": "torchmetrics FrechetInceptionDistance + CLIPScore (openai/clip-vit-base-patch32)"
  }
}