Let the fill show the model an open void: mirror depth 0 means no ring and nothing known beyond the band

This commit is contained in:
2026-09-20 10:56:38 +02:00
parent 3de109fbd1
commit b1c99b5796
8 changed files with 155 additions and 31 deletions
+9 -4
View File
@@ -104,11 +104,16 @@ the dataset licence restricts models trained on it by name.
| File | Source | Trained on | Used by |
|---|---|---|---|
| `inpaint/migan-512.onnx` | `migan_512_places2.pt` from `https://github.com/Picsart-AI-Research/MI-GAN` (Sargsyan et al., ICCV 2023) | Places2, by the authors | the panorama border fill (FR-MRG-4) |
| `inpaint/migan-512.onnx` | `migan_512_places2.pt` from `https://github.com/Picsart-AI-Research/MI-GAN` (Sargsyan et al., ICCV 2023), **fine-tuned** in the `darkroom-infill` repository (2026-09-20) | Places2 by the authors, then ~7 400 of the maintainer's own photographs with border-shaped voids | the panorama border fill (FR-MRG-4) |
Exported by `tools/export-migan.sh`: the bare 512 generator at a fixed
`1×4×512×512`, six operator types. The tiling, the context and the blend are
Rust (`dr_pano::fill`).
The bare 512 generator at a fixed `1×4×512×512`, six operator types; the
tiling, the context and the blend are Rust (`dr_pano::fill`). Since
2026-09-20 the shipped file is the fine-tune (`docs/panorama.md` §14),
exported by `python -m infill.export` in `darkroom-infill`;
`tools/export-migan.sh` still produces the stock generator from the upstream
checkpoint, which the fine-tune starts from. The fine-tuned weights are a
derivative of the MIT weights trained on photographs the maintainer owns,
and carry the same MIT grant.
**MIT, code and weights alike** — `LICENSE` and `LICENSE-WEIGHTS` in the
repository, both read on 2026-09-19, both the plain MIT text with no further