{
  "description" : "Qwen-Image-2.1 VAE decoder, 512x512, fp32: latents_packed [1,1024,64] (sampler output, normalised) -> image [1,4,512,512] RGBA in [-1,1]; unpack and latents*std+mean inside the graph. Source: Qwen\/Qwen-Image-2.1@790c926.",
  "assetVersion" : "2.0",
  "license" : "qwen-research",
  "creationDate" : "20260925T071145Z",
  "producer" : "coreai-core 1.0.0b2"
}