Archiver Rough
Good for
An aggressive restoration model from the Archivist suite for severely degraded footage. It attempts to reconstruct heavily damaged or lost details through hallucination. Note: its capabilities overlap with the RGB model, but it focuses more on structural integrity than color noise.
This model is optimized for input resolutions between 720p and 1080p. Using it on significantly different resolutions may produce suboptimal results.
All Archivist models are trained on a custom dataset generated by a physics-based degradation simulator. Recommended Workflow: Use Archivist to fix physical defects, then pass the result through DRUNet (low strength) to stabilize.
Training details (6)
- Date
- 2025-12-17
- Dataset
- Custom dataset (~1800 images) of classic cel animation (1940s-1980s) processed with the Project Degrader physics-based pipeline.
- Dataset size
- 1800
- Training iterations
- 493000
- Training HR size
- 256
- Training OTF
- Yes

