SynLayers Real-World Decomposition

Upload a single image and run the full pipeline in one step:

  1. VLM for whole-caption + bounding-box detection
  2. SynLayers real-image layer decomposition This Space can run either on a dedicated GPU Space or on Hugging Face ZeroGPU. The first request may still take time while Python modules and model objects are initialized. Model files are prefetched during Space startup, and initialized model objects are reused while the process stays alive.

Runtime Status

  • SPACE_ID: SynLayers/synlayers
  • ACCELERATOR: zero
  • HF_HOME: /home/user/.cache/huggingface
  • Stage 1 bbox repo/path: SynLayers/Bbox-caption-8b
  • Stage 2 repo: SynLayers/synlayers

Model Asset Prefetch

  • Prefetch enabled: True
  • Stage 1 bbox model: SynLayers/Bbox-caption-8b
  • Stage 2 model repo: SynLayers/synlayers
  • Stage 1 files prefetched: True
  • Stage 2 assets prefetched: True

ZeroGPU

  • ZeroGPU mode: True
  • Requested GPU size: large
  • Requested max duration: 500 seconds
  • CUDA probe outside @spaces.GPU: True

This Space is configured for Hugging Face ZeroGPU. A shared GPU is requested on demand when you click Run Full Pipeline. Model files are prefetched during Space startup, before the ZeroGPU function is called. After the first successful request, model objects are reused while the Python process stays alive.

128 2048