mafiosnik
patreon
[Release] - enhancr Pro 0.9.9 | SCUNet, SwinIR (TensorRT) & DirectML Backend
🕑 Added 2023-06-04 19:33:03 +0000 UTCChanges:
- Added fp16 i/o to RIFE
- Replaced deprecated cupy.cuda.compile_with_cache with cupy.RawModule
- Updated to Python 3.11, TensorRT 8.6.1, cudatoolkit 12.1, PyTorch 2.1.0 nightly & Vapoursynth R62
- Implemented SwinIR (TensorRT)
- Switched webm muxer back to ffmpeg
- Filtering out generic VapourSynth error now, due to people not getting that it's not an error
- Added RealESRGAN (DirectML)
- Removed blur on Windows 10
- Rewrote Queue Backend partially
- Implemented CAIN (DirectML)
- Added dynamic axes to RVPV2 -> extra step for exporting to onnx isn't necessary anymore
- Added DPIR (DirectML)
- Updated ThemeEngine to make UI a bit more consistent
- Implemented SCUNet (TensorRT)
- Small UI Changes overall
Bugfixes:
- Fixed Tiling for ShuffleCUGAN (NCNN)
- Changed optShape calculation for DPIR
- Fixed Subtitle Check when selecting mp4 output container
- Re-enabled CUDNN tactics in TensorRT (thanks nvidia)
- Fixed RIFE TensorRT engine build crashing
- Scaled down Preview encoder (This fixes most "[h264/h265/av1_nvenc @ xxxxxxxxxxxxxxx] No capable devices found" errors. See FAQ in wiki for more infos.)
- Fixed RVPV2 ONNX conversion
- Added padding to NCNN for resolutions non divisible by 8, due to color channels not being put together properly after padding inside model
- Fixed memory leak when reading media metadata that would occur when processing a lot of items in queue
- Fixed duration formatting in Media Info
- Discord Rich Presence properly resetes to idle state when process is completed/canceled now
- Fixed custom pth ESRGAN models
- Removed fp16 i/o from RVPV1 (TRT) to make it work again
Download: https://enhancr.app/setup/enhancr-setup-0.9.9-b30f65e.exe
Join the discord if you haven't yet: https://dsc.gg//enhancr
Comments
Intelextreme13
Any updates coming soon?
BRUNO RANTIN PO
This membership was supposed to have an embeddable python distribution, right? Where is it?
Gil Fregoso
Como puedo acceder a las versiones "pro" de los modelos de ia?
Esau Asael Moya
Same problem
Yikang Gong
I wonder if you will update to RIFE 4.11 and make it as a TRT model?
mafiosnik
You probably set the cache folder to your desktop then, in the settings
Blake Andersen
I installed 0.9.9 and as soon as I clicked "Enhance Videos" it created a "preview" folder in my Desktop and DELETED every other file I had on the desktop!
mafiosnik
Fixed now.
Aion
Hello, i can't download your link of 0.9.9. it's said "404 not found" , and i can't pass in rule channel on Discord after i press button "I accept the rules", it's said "This interaction failed"
João Costa
I'm having a small issue queuing multiple files. I'll queue a file for say, restoration, and chain an interpolation task after. If I then add another restoration of a different file and try chaining an interpolation, the input video of the new interpolation is the same as the first interpolation, basically not capturing the fact there is now another file in the mix. What I'm trying to achieve is having a batch job where I'll throw a few episodes at it that need to be both restored and interpolated, but as it is now, I can't seem to do it.
