SnJake
/

Baikal-Swin-Anime

computer-vision

image-restoration

image-enhancement

super-resolution

Model card Files Files and versions

SnJake commited on Jan 6

Commit

efb8e8f

·

verified ·

1 Parent(s): 024f83d

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -47,6 +47,8 @@ V2:
 - Slightly sharper output, no edge noise artifacts.
 - Epochs: 20 (For now)
 - Dataset: 49,606 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
 Training code is included in `training_code/` for reference.

 - Slightly sharper output, no edge noise artifacts.
 - Epochs: 20 (For now)
 - Dataset: 49,606 images from Danbooru2024: https://huggingface.co/datasets/deepghs/danbooru2024
+- Perceptual backbone: convnextv2_tiny.fcmae_ft_in22k_in1k, fine‑tuned on anime to improve feature sensitivity.
+- Loss schedule: gradual ramp‑in of perceptual/auxiliary losses for stable training.
 Training code is included in `training_code/` for reference.