How d-ogi/watermarkremover-ai works
WatermarkRemover-AI detects watermark regions with Florence-2, then removes them through LaMA inpainting; users can run this workflow from the desktop GUI or CLI, with image, video, batch, preview, and mask options. The GUI delegates processing to the CLI and prepares models in a worker. The graph also shows the separate model-cache and LaMA execution layers. UI-to-bridge wiring and some unsampled video details are not fully visible in the excerpts, so uncertain links are omitted or marked unverified.
Main entry points: remwm.py CLI workflow · remwmgui.py Desktop GUI bridge · runtime.py LaMA inference · desktop_models.py Model preparation worker
Components 16
User interfaces
- Desktop entry
desktop_main.py - Desktop GUI bridge
remwmgui.py - Web UI
ui/index.html
Detection and removal
- CLI workflow
remwm.py - Watermark detection
remwm.py - Mask construction
remwm.py - Image and video processing
remwm.py
Model preparation
- Florence assets
model_assets.py - Hugging Face model source
- LaMA inference
lama_inpaint/runtime.py - Inpaint crop and composite
lama_inpaint/processing.py - Verified LaMA cache
lama_inpaint/model_store.py - LaMA model source
Desktop runtime
- Model preparation worker
desktop_models.py - Runtime paths and workers
desktop_runtime.py
Other components
- User
Connections 17
- User → Desktop entry: launches
README.md - User → CLI workflow: invokes
README.md - Desktop entry → Desktop GUI bridge: starts
desktop_main.py - Web UI → Desktop GUI bridge: calls bridge
- Desktop GUI bridge → Model preparation worker: prepares models
remwmgui.py - Model preparation worker → Runtime paths and workers: uses worker settings
desktop_models.py - Model preparation worker → Florence assets: runs preparation
desktop_models.py - Florence assets → Hugging Face model source: downloads
model_assets.py - Desktop GUI bridge → CLI workflow: starts processing
remwmgui.py - CLI workflow → Florence assets: loads detection assets
remwm.py - CLI workflow → Watermark detection: runs detection
remwm.py - Watermark detection → Mask construction: builds masks
remwm.py - CLI workflow → Image and video processing: processes media
remwm.py - Image and video processing → LaMA inference: inpaints regions
remwm.py - LaMA inference → Verified LaMA cache: verifies and loads
lama_inpaint/runtime.py - LaMA inference → Inpaint crop and composite: delegates compositing
lama_inpaint/runtime.py - Verified LaMA cache → LaMA model source: downloads weights
lama_inpaint/model_store.py