qwen_image_i2i_2511.json

{
    "infer_steps": 40,
    "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{}<|im_end|>\n<|im_start|>assistant\n",
    "prompt_template_encode_start_idx": 64,
    "resize_mode": "adaptive",
    "attn_type": "mlu_flash_attn",
    "enable_cfg": true,
    "sample_guide_scale": 4.0,
    "CONDITION_IMAGE_SIZE": 147456,
    "USE_IMAGE_ID_IN_PROMPT": true,
    "modulate_type": "torch",
    "rope_type": "torch",
    "layer_norm_type": "torch",
    "rms_norm_type": "mlu_rms_norm"
}