config.json

{
  "model_type": "s1-omni-image",
  "architectures": [
    "S1OmniImageModel"
  ],
  "prefixes": {
    "qwen3_vl": "qwen3_vl.",
    "transformer": "transformer.",
    "vae": "vae.",
    "alignment_mlp": "alignment_mlp."
  },
  "qwen3_vl_config": {
    "architectures": [
      "Qwen3VLForConditionalGeneration"
    ],
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "hidden_size": 4096,
    "image_token_id": 151655,
    "model_type": "qwen3_vl",
    "pad_token_id": 151643,
    "text_config": {
      "attention_bias": false,
      "attention_dropout": 0.0,
      "bos_token_id": 151643,
      "dtype": "bfloat16",
      "eos_token_id": 151645,
      "head_dim": 128,
      "hidden_act": "silu",
      "hidden_size": 4096,
      "initializer_range": 0.02,
      "intermediate_size": 12288,
      "max_position_embeddings": 262144,
      "model_type": "qwen3_vl_text",
      "num_attention_heads": 32,
      "num_hidden_layers": 36,
      "num_key_value_heads": 8,
      "pad_token_id": 151643,
      "rms_norm_eps": 1e-06,
      "rope_scaling": {
        "mrope_interleaved": true,
        "mrope_section": [
          24,
          20,
          20
        ],
        "rope_type": "default"
      },
      "rope_theta": 5000000,
      "use_cache": false,
      "vocab_size": 151936
    },
    "tie_word_embeddings": false,
    "transformers_version": "4.57.6",
    "video_token_id": 151656,
    "vision_config": {
      "deepstack_visual_indexes": [
        8,
        16,
        24
      ],
      "depth": 27,
      "dtype": "bfloat16",
      "hidden_act": "gelu_pytorch_tanh",
      "hidden_size": 1152,
      "in_channels": 3,
      "initializer_range": 0.02,
      "intermediate_size": 4304,
      "model_type": "qwen3_vl",
      "num_heads": 16,
      "num_position_embeddings": 2304,
      "out_hidden_size": 4096,
      "pad_token_id": 151643,
      "patch_size": 16,
      "spatial_merge_size": 2,
      "temporal_patch_size": 2
    },
    "vision_end_token_id": 151653,
    "vision_start_token_id": 151652
  },
  "transformer_config": {
    "_class_name": "QwenImageTransformer2DModel",
    "_diffusers_version": "0.36.0.dev0",
    "attention_head_dim": 128,
    "axes_dims_rope": [
      16,
      56,
      56
    ],
    "guidance_embeds": false,
    "in_channels": 64,
    "joint_attention_dim": 3584,
    "num_attention_heads": 24,
    "num_layers": 60,
    "out_channels": 16,
    "patch_size": 2,
    "zero_cond_t": true
  },
  "vae_config": {
    "_class_name": "AutoencoderKLQwenImage",
    "_diffusers_version": "0.36.0.dev0",
    "attn_scales": [],
    "base_dim": 96,
    "dim_mult": [
      1,
      2,
      4,
      4
    ],
    "dropout": 0.0,
    "latents_mean": [
      -0.7571,
      -0.7089,
      -0.9113,
      0.1075,
      -0.1745,
      0.9653,
      -0.1517,
      1.5508,
      0.4134,
      -0.0715,
      0.5517,
      -0.3632,
      -0.1922,
      -0.9497,
      0.2503,
      -0.2921
    ],
    "latents_std": [
      2.8184,
      1.4541,
      2.3275,
      2.6558,
      1.2196,
      1.7708,
      2.6052,
      2.0743,
      3.2687,
      2.1526,
      2.8652,
      1.5579,
      1.6382,
      1.1253,
      2.8251,
      1.916
    ],
    "num_res_blocks": 2,
    "temperal_downsample": [
      false,
      true,
      true
    ],
    "z_dim": 16
  },
  "scheduler_config": {
    "_class_name": "FlowMatchEulerDiscreteScheduler",
    "_diffusers_version": "0.36.0.dev0",
    "base_image_seq_len": 256,
    "base_shift": 0.5,
    "invert_sigmas": false,
    "max_image_seq_len": 8192,
    "max_shift": 0.9,
    "num_train_timesteps": 1000,
    "shift": 1.0,
    "shift_terminal": 0.02,
    "stochastic_sampling": false,
    "time_shift_type": "exponential",
    "use_beta_sigmas": false,
    "use_dynamic_shifting": true,
    "use_exponential_sigmas": false,
    "use_karras_sigmas": false
  },
  "alignment_mlp": {
    "input_dim": 4096,
    "output_dim": 3584,
    "hidden_dim": 4096,
    "type": "mlp"
  },
  "special_tokens": {
    "think_start": "<think>",
    "think_end": "</think>",
    "image_gen_start": "<image_gen>",
    "image_gen_end": "</image_gen>",
    "image_edit_start": "<image_edit>",
    "image_edit_end": "</image_edit>"
  },
  "generation": {
    "max_new_tokens": 2048,
    "temperature": 0.7,
    "top_p": 0.9,
    "do_sample": true
  },
  "image_generation": {
    "default_height": 1024,
    "default_width": 1024,
    "num_inference_steps": 50,
    "guidance_scale": 1.0,
    "true_cfg_scale": 4.0
  }
}