llama.cpp now has an official website: https://t.co/vztdUpdBWL
Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.
While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).
We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.
🦙 Anyone else miss Milkdrop / Winamp?
🔉 Load audio file
⌨️ Press 'SPACE' to move to the next preset
⌨️ Press 'R' to move to a random preset
⌨️ Press 'H' to hide the menu
💾 Loads .milk presets
https://t.co/4t4AhJBC7I
How do today's image models really perform when stress-tested on real-world tasks?
Introducing ImagenWorld — a benchmark with explainable human evaluation revealing where and why models fail.
- 6 generation & editing tasks × 6 visual domains
- 20K+ human annotations with object-level issue tags
- 14 models evaluated across artwork, photos, screenshots & more
🧵 👇
New paper: You can make ChatGPT 2x as creative with one sentence.
Ever notice how LLMs all sound the same?
They know 100+ jokes but only ever tell one.
Every blog intro: "In today's digital landscape..."
We figured out why – and how to unlock the rest 🔓
Copy-paste prompt: 🧵
See Native Audio in action 🤠🦊 Our "Mumble Jumble" demo in Google AI Studio showcases the Live API's advanced voice capabilities: natural flow, distinct tone, emotion, and multilingual support.
Art with o3 😉
Chrononaut No. 3 was conceived as a controlled experiment in narrative macro‑photography, created entirely within an AI‑driven image‑synthesis pipeline. The result is a visual paradox that pulls the viewer simultaneously into the past and a speculative tomorrow.
Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems view” of LLMs and wrote a little textbook called “How To Scale Your Model” which we’re releasing today. 1/n
DeepSeek just dropped a series of gpt-4o-like models 🔥
Janus-Pro is a new series of LLMs with image and text input and image and text output 🤯
Runs conveniently in consumer GPUs with 1B and 7B parameters, link to model and the demo in the next one
Gemini 2.0 drops the beat.
Watch the video all the way through — I had four legit "no way it did that" reactions when @JonPTaylor sent this to me.
"It looks like it's only hitting on the first beat of each bar."
This is Jon collaborating with Gemini to create a song in @Ableton Live.
Jon is using the Multimodal Live API to stream audio and video to Gemini and have a conversation about the song he's creating.
Excited to announce LTX-Video!
Our new text-to-video model generates stunning, high-quality videos faster than real-time—5 seconds of 24fps video at 768x512 in just 4 seconds on an Nvidia H100! ⚡
We’re open-sourcing the code & weights. Check out the results 🎥👇
FLUX.1 Tools from @bfl_ml just dropped with Day 1 support in ComfyUI!
- FLUX.1 Fill -> Great for filling in or expanding images
- FLUX.1 Redux -> Making different versions of an image
- Controlnets -> Control images using canny or depth guides
Here are some images👇
The community has uploaded more than 7000 Flux[dev] LoRAs to @huggingface 🤗🎊
Browse them all 🔍 and test them out for free 🖼️ ✨
▶️ https://t.co/sxj2EDAVvJ
Congrats to @recraftai team for achieving state of the art in image generation ai!
London continues to be one of the top ai hubs globally & hopefully we will see more companies building great things here 🙏
✨ 🖼️ Generate images with consistent characters without any fine tuning nor training. Consistory is a training-free approach to maintaining subject consistency between text-to-image generations on pretrained models. #NVIDIAResearch
🎨 Test it here: https://t.co/KteU59xy54