{
  "architecture": "latent-mmdit",
  "objective": "rectified-flow",
  "dit": {
    "dim": 512,
    "depth": 16,
    "heads": 8,
    "patch": 2,
    "latent_ch": 4,
    "latent_size": 32,
    "mlp_hidden": 1408,
    "t5_len": 32
  },
  "vae": "madebyollin/sdxl-vae-fp16-fix",
  "text_encoders": {
    "joint_stream": "google/flan-t5-base",
    "global_conditioning": "openai/clip-vit-base-patch32"
  },
  "max_tokens": {
    "t5": 32,
    "clip": 40
  },
  "trainable_parameters": 155090448,
  "total_parameters_incl_frozen": 411538807,
  "sampling": {
    "steps": 50,
    "cfg": 3.0
  },
  "training": {
    "steps": 150000,
    "batch": 192,
    "dataset": "undefined443/cc12m-wds-coco-recaptioned, 2986571 images",
    "final_val_loss": 0.7982857534661889
  },
  "eval": {
    "fid": 23.62,
    "clip_score": 30.43,
    "cfg_sweep": [
      {"cfg": 2.0, "fid": 25.65, "clip_score": 29.65},
      {"cfg": 3.0, "fid": 23.62, "clip_score": 30.43},
      {"cfg": 4.0, "fid": 23.77, "clip_score": 30.81},
      {"cfg": 5.0, "fid": 24.42, "clip_score": 31.06},
      {"cfg": 6.0, "fid": 25.10, "clip_score": 31.12},
      {"cfg": 7.0, "fid": 26.26, "clip_score": 31.16},
      {"cfg": 8.0, "fid": 26.87, "clip_score": 31.17}
    ],
    "n": 5000,
    "dataset": "MS-COCO val2014, 256 center crop",
    "protocol": "torchmetrics FrechetInceptionDistance + CLIPScore (openai/clip-vit-base-patch32)"
  }
}