microscope/model_summary.json

{
  "kind": "zimage",
  "pipeline": {
    "_class_name": "ZImagePipeline",
    "_diffusers_version": "0.36.0.dev0",
    "scheduler": [
      "diffusers",
      "FlowMatchEulerDiscreteScheduler"
    ],
    "text_encoder": [
      "transformers",
      "Qwen3Model"
    ],
    "tokenizer": [
      "transformers",
      "Qwen2Tokenizer"
    ],
    "transformer": [
      "diffusers",
      "ZImageTransformer2DModel"
    ],
    "vae": [
      "diffusers",
      "AutoencoderKL"
    ]
  },
  "text_encoder": {
    "config": {
      "architectures": [
        "Qwen3ForCausalLM"
      ],
      "attention_bias": false,
      "attention_dropout": 0.0,
      "bos_token_id": 151643,
      "eos_token_id": 151645,
      "head_dim": 128,
      "hidden_act": "silu",
      "hidden_size": 2560,
      "initializer_range": 0.02,
      "intermediate_size": 9728,
      "max_position_embeddings": 40960,
      "max_window_layers": 36,
      "model_type": "qwen3",
      "num_attention_heads": 32,
      "num_hidden_layers": 36,
      "num_key_value_heads": 8,
      "rms_norm_eps": 1e-06,
      "rope_scaling": null,
      "rope_theta": 1000000,
      "sliding_window": null,
      "tie_word_embeddings": true,
      "torch_dtype": "bfloat16",
      "transformers_version": "4.51.0",
      "use_cache": true,
      "use_sliding_window": false,
      "vocab_size": 151936
    },
    "params": 4022468096
  },
  "transformer": {
    "config": {
      "_class_name": "ZImageTransformer2DModel",
      "_diffusers_version": "0.36.0.dev0",
      "all_f_patch_size": [
        1
      ],
      "all_patch_size": [
        2
      ],
      "axes_dims": [
        32,
        48,
        48
      ],
      "axes_lens": [
        1536,
        512,
        512
      ],
      "cap_feat_dim": 2560,
      "dim": 3840,
      "in_channels": 16,
      "n_heads": 30,
      "n_kv_heads": 30,
      "n_layers": 30,
      "n_refiner_layers": 2,
      "norm_eps": 1e-05,
      "qk_norm": true,
      "rope_theta": 256.0,
      "t_scale": 1000.0
    },
    "params": 6154908736
  },
  "vae": {
    "config": {
      "_class_name": "AutoencoderKL",
      "_diffusers_version": "0.36.0.dev0",
      "_name_or_path": "flux-dev",
      "act_fn": "silu",
      "block_out_channels": [
        128,
        256,
        512,
        512
      ],
      "down_block_types": [
        "DownEncoderBlock2D",
        "DownEncoderBlock2D",
        "DownEncoderBlock2D",
        "DownEncoderBlock2D"
      ],
      "force_upcast": true,
      "in_channels": 3,
      "latent_channels": 16,
      "latents_mean": null,
      "latents_std": null,
      "layers_per_block": 2,
      "mid_block_add_attention": true,
      "norm_num_groups": 32,
      "out_channels": 3,
      "sample_size": 1024,
      "scaling_factor": 0.3611,
      "shift_factor": 0.1159,
      "up_block_types": [
        "UpDecoderBlock2D",
        "UpDecoderBlock2D",
        "UpDecoderBlock2D",
        "UpDecoderBlock2D"
      ],
      "use_post_quant_conv": false,
      "use_quant_conv": false
    },
    "params": 83819683
  },
  "scheduler": {
    "config": {
      "_class_name": "FlowMatchEulerDiscreteScheduler",
      "_diffusers_version": "0.36.0.dev0",
      "num_train_timesteps": 1000,
      "use_dynamic_shifting": false,
      "shift": 3.0
    }
  }
}