Made Nano Banana to transform freestyle drawings into image illustrations (from free-style drawing to image). It also supports other options like image generation and single or multiple image edits. Built with the Gemini API, powered by GCP. App: …no-banana-aio-op72ohwdda-uw.a.run.app

Understanding GPU Architecture from Cornell cvw.cac.cornell.edu/gpu-architectu… During a low-level discussion at a casual meetup, many folks were interested in understanding GPUs more closely. While CPUs optimize for complex control flow (see those big cores + caches), the GPUs maximize

This is cool! We’ve been building something along similar lines in academia: Generative Blocks World. No magic here—just an intuitive pipeline grounded in decades of work on primitive decomposition in computer vision. The inspiration goes all the way back to one of the earliest

Awesome! Let’s get started with the Qwen3-VL notebook in the near future.🌟

Another new Google Gemini model "Oceanreef" is being tested in LmArena The model is likely related to the "Oceanstone" model, which appeared 2 days ago

A toolkit for your ease to use Qwen3-ASR!

While researching GPU architecture further, I found Kostas Anagnostou's recent blog post, "GPU utilisation and performance improvements". Quite interesting insights on GPU perf, read on! interplayoflight.wordpress.com/2025/08/29/gpu…

I love MiniCPM-V 4.5, it's underrated it's only 8B yet great in factual correction + thinking 💬 as they claim, gpt-4o level VLM on-device 👏 great work OpenBMB

IBM just released small swiss army knife for the document models: granite-docling-258M 🔥 not only a document converter but also can do document question answering, understand multiple languages 🤯 with Apache 2.0 license 👏

⚡️Ling-flash-2.0⚡️ is now open source. 100B MoE LLM • only 6.1B active params --> 3x faster than 36B dense (200+ tok/s on H20) --> Beats ~40B dense LLM on complex reasoning --> Powerful coding and frontend development Small activation. Big performance.

1. This LoRA is called Qwen-Image-HeadshotX (source link below). It provides precise portrait rendering with a strong focus on realism.👇🏻 huggingface.co/prithivMLmods/…

This has to be one of the best GPU programming resources I've found - the GPU Glossary from Modal breaks down complex concepts with clear visuals and explanations, from CUDA architecture to Tensor Cores to CTAs. modal.com/gpu-glossary

new maths videos coming soon :))

GenExam: The first multidisciplinary text-to-image exam is now on Hugging Face This new benchmark challenges T2I models with 1,000 rigorous, exam-style prompts across 10 subjects. It comes with ground-truth images and detailed scoring for semantic correctness and visual

ByteDance unveils SAIL-VL2, a SOTA vision-language foundation model. It achieves comprehensive multimodal understanding and reasoning, outperforming at 2B & 8B scales.

Just: import trackio as wandb

Looks good at portraits :)

After a while, I’ve migrated the app’s tech stack to make it compatible for deployment on HF Spaces. Nano Banana AIO (Wrapper) is used for manipulating free-style drawings into images, (multi-image editing, image generation, etc.). 🍌🤗 Space: huggingface.co/spaces/prithiv…

SAIL-VL2 Technical Report

A new era for 360-degree vision in AI, co-authored by Insta360! PANORAMA introduces a revolutionary architecture for omnidirectional vision in embodied AI, offering holistic environmental awareness. It addresses key challenges in data, models, and applications.