{
  "model": "realvisxl-v4.0-lightning",
  "pipeline": "StableDiffusionXLPipeline",
  "variant": "fp16-encoders + TAESDXL",
  "dsp_arch": 75,
  "skel": "libQnnHtpV75Skel.so",
  "qairt_runtime_required": "2.40",
  "quantization": "W8A16",
  "resolution": 1024,
  "latent": [1, 4, 128, 128],
  "scheduler": "EulerDiscrete",
  "steps_default": 6,
  "guidance_scale": 0.0,
  "cross_attention_dim": 2048,
  "vae_scaling_factor": 0.13025,
  "text_encoders": {
    "text_encoder_1": "CLIP-L (penultimate, hidden -2) -> [1,77,768]",
    "text_encoder_2": "OpenCLIP-bigG (+projection) -> last_hidden [1,77,1280] + pooled [1,1280]"
  },
  "text_embedding": "concat CLIP-L[768] ++ bigG[1280] -> [1,77,2048]",
  "host_emb": "sdxl_emb_mlp.bin -> emb[1,1280] per step (fold-proofs timestep + add_time)",
  "vae": "TAESDXL CPU tiny-VAE (taesdxl_decoder.mnn) via --vae_mnn, SDXL_VAE_BACKEND=cpu",
  "graph_name": "model",
  "io_contract": "ours-sdxl-emb"
}