@cyrildiagne.bsky.social - Cyril Diagne

19 Jan 2026 07:45 +0000

FLUX.2 klein inference in pure C, written in a weekend with 0 manual code [contains quote post or other embedded content]

07 Mar 2025 17:08 +0000

Alright who’s making this

06 Dec 2024 09:48 +0000

Align3R: estimates camera poses and consistent depth maps from monocular videos. Combining it with trackers like Cotracker3 or SAM2 could unlock many fun applications! (cf: VideoDoodles by Yu & al) Project page (with demo): https://igl-hkust.github.io/Align3R.github.io Code: https://github.com/jiah-cloud/Align3R

04 Dec 2024 09:41 +0000

Am I the only one amazed that this is what 2*4TB (with thermal case) looks like now?

28 Nov 2024 10:38 +0000

Oh no 😂 I’m torn between rofl for this troll and a fear to see this little drama escalating [contains quote post or other embedded content]

27 Nov 2024 16:42 +0000

The past few months have been... intense! There's still quite some work to do before the finish line, but excited to launch in the coming weeks 💪⚡️

22 Nov 2024 08:38 +0000

Adobe Podcast V2 is a really impressive audio enhancer. Is there any open-source tech close to it? https://bsky.app/profile/pinsky.xyz/post/3lbfhsujqoc2m [contains quote post or other embedded content]

21 Nov 2024 08:17 +0000

SAMURAI: improve the tracking robustness of SAM2 with 2 main contributions: - adding motion information to the mask selection - curating the memory bank based on motion cues Project: yangchris11.github.io/samurai Code: https://github.com/yangchris11/samurai Paper: arxiv.org/abs/2411.11922

20 Nov 2024 09:35 +0000

Pyramid Flow is quite impressive for img2video, given than it was only trained on public datasets. Clearly not as dynamic and stable as commercial solutions, but the gap seems to be closing https://github.com/jy0205/Pyramid-Flow

20 Nov 2024 09:31 +0000

A bit surprised with this data from Clerk on sign-in methods preferences: From a sample of 2.5M sign-in, <2% of users chose to use magic links.

19 Nov 2024 09:18 +0000

"A nicely maintained and over-spec’d server just has a smell to it" - great writeup by @kcimc.bsky.social benchmarking various cloud GPU providers for a realtime diffusion installation: https://kcimc.medium.com/realtime-diffusion-in-the-cloud-f497e66d4f92

18 Nov 2024 09:42 +0000

Very cool idea for working with videos and transformers: remove duplicate patches and add length embeddings instead. They get a 40% speedup finetuning Vit-L using example packing. Run-Length Tokenization (NeurIPS 2024 spotlight): Project: rccchoudhury.github.io/rlt Code: https://github.com/rccchoudhury/rlt

15 Nov 2024 22:27 +0000

Hello there! I’m an AI indie hacker based in Paris. I love everything related to generative AI, from research papers and techniques to cool AI content, frontend dev…etc. I’m currently working on generative video models, and working hard to do a public release in the coming weeks. Cheers ✌️