mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-20 12:37:12 +02:00
Allow verified-text restoration on tiled images
Tile the Qwen VAE donor the same way as the global pass. Glyph restore already runs on the blended full frame, so the old tile ban was an artificial gate.
This commit is contained in:
+3
-2
@@ -609,8 +609,9 @@ engine.remove_watermark(
|
||||
|
||||
Install `remove-ai-watermarks[text-restoration]`. The manifest schema and safety
|
||||
constraints are documented in the CLI guide. The engine verifies its decoded RGB
|
||||
hash before loading the diffusion models and rejects SDXL, tiling, downscaling, and
|
||||
postprocessing combinations that were not evaluated. `InvisibleOptions` exposes the
|
||||
hash before loading the diffusion models and rejects SDXL, downscaling, and
|
||||
postprocessing combinations that were not evaluated. Tiling is allowed: the VAE
|
||||
donor uses the same overlapping tiles as the global pass. `InvisibleOptions` exposes the
|
||||
same field for `remove_all`; after a visible-stage edit, the manifest must be built
|
||||
against the staged pixels rather than the pristine source.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user