 Aarni Koskela
|
3d31d5c27b
SwinIR: pass model.scale
|
1 年之前 |
|
Aarni Koskela
|
dfdc51246c
SwinIR: use prefer_half
|
1 年之前 |
|
Aarni Koskela
|
cf14a6a7aa
Refactor upscale_2 helper out of ScuNET/SwinIR; make sure devices are right
|
1 年之前 |
|
Aarni Koskela
|
6f86b62a1b
Deduplicate tiled inference code from SwinIR/ScuNET
|
1 年之前 |
|
Aarni Koskela
|
777af661a2
Be more clear about Spandrel model nomenclature
|
1 年之前 |
|
Aarni Koskela
|
4ad0c0c0a8
Verify architecture for loaded Spandrel models
|
1 年之前 |
|
Aarni Koskela
|
b0f5934234
Use Spandrel for upscaling and face restoration architectures (aside from GFPGAN and LDSR)
|
1 年之前 |
 SiYu Wu
|
44d66daaad
add option SWIN_torch_compile to accelerate SwinIR upscale using torch.compile()
|
2 年之前 |
 AUTOMATIC1111
|
da8916f926
added torch.mps.empty_cache() to torch_gc()
|
2 年之前 |
|
Aarni Koskela
|
2667f47ffb
Remove stray space from SwinIR model URL
|
2 年之前 |
|
Aarni Koskela
|
bf67a5dcf4
Upscaler.load_model: don't return None, just use exceptions
|
2 年之前 |
|
Aarni Koskela
|
0afbc0c235
Fix up `if "http" in ...:` to be more sensible startswiths
|
2 年之前 |
|
Aarni Koskela
|
89352a2f52
Move `load_file_from_url` to modelloader
|
2 年之前 |
|
AUTOMATIC
|
df6fffb054
change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>
|
2 年之前 |
|
Aarni Koskela
|
49a55b410b
Autofix Ruff W (not W605) (mostly whitespace)
|
2 年之前 |
|
AUTOMATIC
|
f741a98bac
imports cleanup for ruff
|
2 年之前 |
|
AUTOMATIC
|
96d6ca4199
manual fixes for ruff
|
2 年之前 |
 catboxanon
|
3c47b05036
Also make SwinIR skippable
|
2 年之前 |
|
catboxanon
|
f993525820
Make SwinIR interruptible
|
2 年之前 |
|
AUTOMATIC
|
cefb5d6d7d
fix accessing options when they are not ready for SwinIR.
|
2 年之前 |
|
AUTOMATIC
|
b6e5edd746
add built-in extension system
|
2 年之前 |
