Stars and mentions
Last 30 days, Oct 4 – Nov 2
Package downloads
Cumulative recorded downloads · since 2026-04-09
Across 1 known packages in repositories wiltodelta owns. Cumulative totals include recorded downloads before the selected range. Missing observations leave gaps; totals may be incomplete. PyPI excludes known mirrors.
Top repositories
wiltodelta’s repositories ranked by pull request authors, as on trending.
Contributes to
Repositories outside wiltodelta’s account where wiltodelta opened or reviewed pull requests in the past 365 days.
Who noticed wiltodelta
Everyone who starred or forked wiltodelta’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
- Gold
- 01st place finishes
- Silver
- 02nd place finishes
- Bronze
- 03rd place finishes
- Awarded repositories
- 0Owned by wiltodelta now
No trending awards yet
None of the repositories wiltodelta owns has finished in the top three of a completed trending day or week, by stars, forks or PR authors. See who is trending now.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
Claude Opus 5.5 and Codex Sol 6.1 spent two weeks and 1,899 scripts trying to land our 10-provider classifier for wiltodelta/remove-ai-watermarks. Google's new Gemini 4 Argon rebuilt the pipeline in 6 scripts, hitting 99.5% blind specificity. Right now it is still running experiments and pushing the metrics further. The DeepSWE v1.1 benchmark backs this up: Gemini 4 Argon scores 77.9% vs 74.2% for Opus 5.5 on long-horizon engineering. I ended up on the max plan across all three labs because each one has a clear job: - Google runs the heavy open-source R&D. - Anthropic still leads on EQ-Bench and creative work. - OpenAI is the best daily driver with limits that actually hold up. What does your model stack look like right now? @ThomasOrTK @AlexanderSivura
刷到个开源工具 Remove-AI-Watermarks，专门清 AI 生成图片或视频里的水印。 Gemini、Nano Banana 的星标它能去，豆包、即梦、Qwen、可灵、元宝、百度这些平台的角标也支持。 视频这块覆盖 Sora、Veo、Seedance、Hailuo、Kling 等平台。 GitHub：wiltodelta/remove-ai-watermarks 可见水印和隐藏水印它都处理，包括谷歌的 SynthID。隐藏水印靠模型重绘打散，效果不错但得有 CUDA 显卡；只清元数据的话，CPU 就够了。 作者也说了，希望只用于处理自己拥有的内容，别拿去针对图库预览图这类保护他人付费内容的水印。 另外还提供了一个在线体验 Demo，可见水印和元数据移除可以直接用。