iiinova — where your digital self keeps evolving

Cyril Diagne @cyrildiagne.bsky.social · 19/01/2026

FLUX.2 klein inference in pure C, written in a weekend with 0 manual code

Reposted by Cyril Diagne

Clément Chadebec @clementchadebec.bsky.social · 13/03/2025

Excited to share our new research at Jasper Research! 🚀 LBM: Latent Bridge Matching for Fast Image-to-Image Translation Try out our @hf.co space for object relighting! 🤗 @gradio-hf.bsky.social demo: huggingface.co/spaces/jaspe... 👉 Paper: arxiv.org/abs/2503.07535 💻 Repo: github.com/gojasper/LBM

2207

Cyril Diagne @cyrildiagne.bsky.social · 06/12/2024

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): igl-hkust.github.io/Align3R.gith... Code: github.com/jiah-cloud/A...

2243

Cyril Diagne @cyrildiagne.bsky.social · 04/12/2024

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

090

Cyril Diagne @cyrildiagne.bsky.social · 28/11/2024

Oh no 😂 I’m torn between rofl for this troll and a fear to see this little drama escalating

170

Cyril Diagne @cyrildiagne.bsky.social · 27/11/2024

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 💪⚡️

2130

Cyril Diagne @cyrildiagne.bsky.social · 22/11/2024

Adobe Podcast V2 is a really impressive audio enhancer. Is there any open-source tech close to it? bsky.app/profile/pins...

281

Cyril Diagne @cyrildiagne.bsky.social · 21/11/2024

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: github.com/yangchris11/... Paper: arxiv.org/abs/2411.11922

0176

Cyril Diagne @cyrildiagne.bsky.social · 20/11/2024

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 github.com/jy0205/Pyram...

040

Cyril Diagne @cyrildiagne.bsky.social · 20/11/2024

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.

021

Cyril Diagne @cyrildiagne.bsky.social · 19/11/2024

"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: kcimc.medium.com/realtime-dif...

kcimc.medium.com

Realtime diffusion in the cloud

In December 2023, I implemented a realtime diffusion toolkit with Daito Manabe and Rhizomatiks. The toolkit is based on SDXL Turbo running…

0122

Cyril Diagne @cyrildiagne.bsky.social · 18/11/2024

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: github.com/rccchoudhury...

1131

Cyril Diagne @cyrildiagne.bsky.social · 15/11/2024

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 ✌️

1200