Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
No packages found.
README badges
Embed a badge in your README or website.
Live mentions · last 30 days
Mentions
பழைய blurry video-களை 4K ஆக்கலாம்.. Real-ESRGAN. Open source, free. Python வேண்டாம்னா exe-ஏ இருக்கு. உன் பழைய clip-அ try பண்ணுவியா ? xinntao/Real-ESRGAN Instagram-லும் பின்தொடருங்கள்: instagram.com
Upscayl: Enlarge Photos with AI, Locally | GitHub Repos You Should Know #014 A tiny photo, enlarged four times in each dimension with Upscayl. Repo: upscayl/upscayl Classification: Worth Knowing We tested the local engine shipped with Upscayl 2.15.0 using Upscayl Standard. The selected model files are byte-identical to Real-ESRGAN’s original realesrgan-x4plus model in its v0.2.5.0 Windows distribution. These are controlled tests: we reduced the reference photos to 160 pixels wide (cat) and 200 pixels wide (rocket), then generated actual 640- and 800-pixel-wide outputs. All before/after crops use matching framing and display size. The ordinary enlargement baseline uses bicubic interpolation. No manually retouched or fake after-images. The comparison wipes are editorial animation, not a recording of processing speed. The demonstration uses the real bundled command-line engine, not a recording of the desktop interface. The model argument shown is an excerpt, not a complete command. Upscayl needs a compatible Vulkan GPU. Our local tests ran with the existing RTX 4090 available. AI estimates details; a sharper output is not guaranteed to be more accurate or to restore the original detail. Licences: Upscayl and its backend AGPL-3.0; selected original Real-ESRGAN model BSD-3-Clause. Other models may have different terms. github.com/upscayl/upscayl/blob/v2.15.0/Real-ESRG… github.com/xinntao/Real-ESRGAN/releases/tag/v0.2.… Photo credits: Chelsea the cat by Stefan van der Walt, CC0; DSCOVR/Falcon 9 photo by SpaceX, public domain. Both distributed through scikit-image. No endorsement implied. scikit-image.org flickr.com What would you upscale? #GitHub #OpenSource #Upscayl
@hAru_mAki_ch 768出力は[Real-ESRGAN](xinntao/Real-ESRGAN)で2倍に拡大できます。元動画と同じフレームで細部を見比べて、追加CUも記録すると、画質改善にどこまでコストをかけるか判断できます。
this is the upscaling algorithm that Claude found: xinntao/real-esrgan