Recent content by Besh

Yes, I use an online AI to upscale 480p to 1080p. I chose the best quality available and it's around 4 hours for every 45min. Yes it's long, but I let it run on the background. You can upscale up to 1080p for free, if you want 4K you have to pay. Best part is the files will never leave your...

I have some very old one that were in .AVI, or TS, I use VLC to convert them to MP4. Also, I move the movies I want to decensored from the HDD were they are stored to a NVME SSD and that almost cut in half the time it take. -Besh

Hi, Out of 372 movies I decensored with Lada, the only one that I had problem with are the FNS (Faleno Star) series. I dont have any problem with FTHTD (Faleno Tube) or FCDSS or even MGOLD but FNS, Lada wont work, which I dont understand why since I can remove mosaic with the rest of their...

Not including Minami Hinano, in a championship like that, is a crime against the Loli community. -Besh

Sadly yes, she's gone but she was a very good prospect when I wrote that in 2024.

It's an AI and it will continue to improve over time. With that said, I do think this awesome collaboration is worth it and has improved a lot since the beginning. It will never be on par with the work done by a native Japanese speaker who translates a movie you pay $250 to have translated. But...

Hi, I tested it with 4 differents movies and everything works well. Took around 43 min on Fidelity/agressive for each movies, thank you for the fix @mei2 Note: During downtime when they are not talking, Whisper AI generate a full japanese recipe ahaha. Example: I used the leftover rice and...

Same, EOFError: EOF when reading a line 2026-03-25 18:33:15 - whisperjav - ERROR - Speech Segmenter failed: Failed to load Silero VAD: EOF when reading a line 2026-03-25 18:33:15 - whisperjav - ERROR - Scene 261/262 failed: Failed to load Silero VAD: EOF when reading a line So I try...

Hi, Not really, at least not reliably with current tools. LADA uses AI trained specifically to reconstruct skin/body textures that were pixelized/mosaicked. It works because the model has learned what that specific type of content looks like under the blur. It's essentially an informed guess...

Hi, Iris-1, Iris-2, Iris-3 are simply different generations of the Iris AI model. Each newer number means the model was re-trained and improved, not just a setting change. Iris-1 First version of the model Focused on face enhancement in degraded footage Sometimes over-smoothed details or...

No need for that, you can remove the mosaic yourself using Lada AI, very simple and take around an hour if you dont have a computer from 2006. I'll show you a before and after and I'm sure you will never watch your favorite movies with the mosaic ever. Before After Enjoy, -Besh

I block on purpose everyone from India, Saudi Arabia and Pakistan. -Besh

They’re behind NAT / firewall / blocked ports A peer can be “real” but unreachable: their ISP blocks incoming connections they’re behind a strict NAT their client isn’t accepting connections their port is closed Result: your client knows they exist, but can’t actually exchange data with them...

Yes, very impressive, best way to see it is a ''before and after'' Combine that with the insane @mei2 google colab for the sub and you will never watch a mosaic movie again! PS: I've DM you the entire way to install and the /command script to process several movies in batch if you decide to use...

Chuck, Gone are the days of downloading the reducing mosaic =) Use LADA AI and remove the mosaic completely! Combined that AI with Whisper JAV 0.7 and this is a game changer. I was sceptical at first but I was speechless when I saw the result. Some exemple of what I acheived with that AI...