qwen_image_i2i_block.json

{
    "batchsize": 1,
    "num_channels_latents": 16,
    "vae_scale_factor": 8,
    "infer_steps": 50,
    "guidance_embeds": false,
    "num_images_per_prompt": 1,
    "vae_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
    ],
    "vae_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
    ],
    "vae_z_dim": 16,
    "feature_caching": "NoCaching",
    "transformer_in_channels": 64,
    "prompt_template_encode": "<|im_start|>system\nDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>\n<|im_start|>assistant\n",
    "prompt_template_encode_start_idx": 64,
    "_auto_resize": true,
    "num_layers": 60,
    "attention_out_dim": 3072,
    "attention_dim_head": 128,
    "axes_dims_rope": [
        16,
        56,
        56
    ],
    "_comment_attn": "in [torch_sdpa, flash_attn3, sage_attn2]",
    "attn_type": "flash_attn3",
    "do_true_cfg": true,
    "true_cfg_scale": 4.0,
    "cpu_offload": true,
    "offload_granularity": "block",
    "mm_config": {}
}