Most AI image detectors work fine in the lab and fail on social media.
The reason is simple. Real photos get compressed, resized and re-uploaded again and again, and detectors trained on clean images read that damage as a sign of fakery. A real photo that has passed through a few platforms often gets flagged as AI-generated.
AIRealNet-2 is built to fix that. It is the upgrade to our original Modotte/AIRealNet, trained on images collected from platforms like Instagram and X, so it has seen the kinds of quality loss and compression real images go through online.
The training set has 98k images, split 50/50 between AI-generated and real, so the model has no class bias to lean on. Personal photos were excluded by design, including AI-edited ones.
The architecture is unchanged: a SwinV2 Tiny backbone with a binary classification head, about 0.2B parameters, working at 256x256 resolution. It stays fast and easy to deploy for research or production.
I built Seekify, a Python tool that turns web search into clean, LLM-ready input for free.
Collecting sources for an LLM workflow usually means juggling search APIs, scraping pages, and cleaning up messy text. Seekify handles that in one place:
- No search API key needed - Structured results with titles, URLs, and snippets - Optional page text extraction so your model gets real content, not just links
Search the web, collect sources, and feed them straight into your pipeline, so you spend less time gathering data and more time building.
It's open source, and I'd love your feedback, ideas, and contributions.
Introducing Live Subtitles, a Windows tray app that captions anything your PC is playing and isn't butt ugly. live and fully local. It runs NVIDIA's Parakeet-unified 0.6B on your GPU, puts words on screen about 0.36 s after they're spoken, and uses less than one CPU core while it does it.
I built a benchmark for it out of real TV, podcasts, earnings calls and a short film. Parakeet-unified scores 12.1% WER there, close to Nemotron streaming's 11.4%, but with much better punctuation and lower worst-case delay. Once a caption is on screen it never gets rewritten or jumps lines, and the overlay disappears when nobody's talking.
No NVIDIA GPU? It falls back to Nemotron on the CPU, which also covers 30 other languages. It can also write SRT/ASS/VTT files for videos on disk.
Windows only. The GPU engine needs an NVIDIA card with ~3.2 GB of free VRAM. MIT.
Edit: the first version of this post said 13.8% vs 17.0%. The replies caught a scoring bug (numbers weren't normalized), so the benchmark now uses Whisper's English normalizer and the numbers above are re-scored.
@Banaxi-Tech stop hiding my comments. AND STOP STEALING PAPERS AND SPREADING MISINFORMATION. your BGA blog is a copy of NSA (deepseek, 2025) branded under your name. literally the same top16 selected blocks, 512 local window, router over block summaries, all you did was change block size from 64 to 128. you didnt cite NSA once but you put a “please cite BGA” bibtex at the bottom. i commented under your post and said that there is no way that you can support claims like: “The Accuracy Should BE WAy better than DSA but untested yet.” you didnt run a single experiment. and the 256x isnt from BGA, its just n/2k with k=2048 so the exact same k DSA uses. if opus wrote this for you, at least read it before posting. i commented again after you hid my comment despite it having constructive and correct feedback and you hid that too. and again. you can hide the truth and just try to get hf post likes..... but is it really the thing that needs to be done? do you really want to take papers and make them yours while barely even changing the params?
admitting your mistakes and doing something about them needs humbleness, intelligence, humanness. i encourage you to admit your mistakes and try to do better next time (at least read what blog your ai wrote or do proper experiments to back your stuff up).
Most NSFW classifiers break the second an image touches the internet.
They look great on pristine benchmarks, but in the wild, every social platform aggressively recompresses, downsamples, and degrades images. The moment JPEG or WebP compression artifacts show up, confidence collapses and false positives spike.
SafeScan was built to survive actual platform pipelines. Trained on 34,000 images under almost every major social media compression profile using a Vision Transformer backbone (google/vit-base-patch16-224). Instead of blunt binary filtering, it breaks decisions down across 5 clear categories:
• safe • drawing • sexy • hentai • porn
The result is a moderation model that actually generalizes to real-world internet feeds instead of fragile, uncompressed datasets. Open-weight and available on Hugging Face:
Most deepfake audio detectors are quietly cheating.
They don’t really listen to the speech — they just look at how long the embedding vector is. Once they figure that out, accuracy looks great on paper and falls apart in the wild.
AIRealNet-Audio was built to stop that shortcut. It forces every feature onto the unit hypersphere (twice) so the model can only use direction, not magnitude. Trained on speech from 100+ different TTS and voice-cloning systems, plus real human recordings under heavy compression and noise.
The result is a detector that actually has to learn the artifacts instead of gaming the feature space.
🕷️ I made a Spider-Man: Miles Morales web-swinging game that runs right in your browser!
Swing, wall-crawl and web-zip through a Spider-Verse style city at sunset: ink outlines, halftone shading, comic caption boxes, "THWIP!"s, wall crashes and all.
🖼️ Nano Banana Editor is now Portrait Editor, now with Qwen-Image-2.1
Some updates to the node-based photo editor 👇
✨ What's new - New name: Nano Banana Editor → Portrait Editor - Qwen-Image-2.1 is the HuggingFace model. It runs on its own ZeroGPU Gradio Space and handles both image editing and text-to-image. FLUX.1-Kontext and Qwen-Image-Edit have been removed. - HuggingFace is the default mode. Sign in with HF and start editing. No API key is needed, and it uses your own ZeroGPU quota. - Bug fix: after signing in with HuggingFace, the app used to switch back to Gemini. You now stay on HuggingFace.
🧩 Gemini and GPT modes are still available for multi-image MERGE nodes.
Pretrained on 4x more tokens than the previous releases (20b vs 5b). Instruct tuned versions are coming soon. Very interesting models are coming soon too (hint: super long context).
Just hit #14 and #15 with out FIRST models on Open SLM Leaderboard. The models were trained on 5B tokens, while competing with similarly sized models trained on more than 6-20x the data.
A new base model Speck1.5-140M being trained right now on a higher quality corpus and will be released soon. SpeckChat3 is coming very soon with 1 million samples, specifically designed to post train small base models.
Also, just to clarify stuff, we will NOT release anything that is NOT MIT licensed EVER. Openness is needed in small language research.
Thanks to everyone supporting the project, and stay tuned for new releases!
SPECK UPDATES: 1 New instruct model tuned on top of Speck1-140M: specklabs/Speck1-140M-Instruct 2 Instruction tuning datasets 2 GGUFs
Much more coming soon: Speck1.1-140M-Instruct that is post trained on SpeckChat2 will be coming very soon New base model Speck1.5-140M is coming with a much higher quality corpus
Thanks to everyone who is already supporting the project, and stay tuned for new releases!
new models coming very soon (both instruct and much better models), with much much higher training scale as i am getting marenostrum5 access soon! we will be looking at 100b-2t token budgets :)
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.
CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.
I built an open-source, local-first screen recorder and timeline editor for macOS and Windows. Record your screen, camera and audio; trim clips, add subtitles and export without an account.
