EdgeFusion

On-Device Text-to-Image Generation

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling

Found this upscaled version of Llama 3 8b

This model has been upscaled from 8b parameters to 11.5b parameters without any continuous pretraining or fine-tuning.

huggingface.co/Replete-AI/Lla…

Software designers of tomorrow should study games like Tiny Glade as they look and behave more like where software will end up:

3D/spatial, adaptive, contextual, high-level abstractions, pleasing

New IPAdapter update to simplify attention masking and regional prompting with IPAdapter. All about it in my new video. Also thanks to OpenArt for becoming a Silver Sponsor!
youtu.be/4jq6VQHyXjg

Copilot kalbimi kazandı❤️

Jeremy abim lütfen tek satırda kod yazmayı bırak🥹

Llama 3 8B running 1.89 tokens/s on a Raspberry Pi 5 is pretty CRAZY

Ctrl-Adapter brings more control to image & video models!

The framework enables things like video control with sparse frames, multi-condition control, and video editing 🔥

Links ⬇️

📢VBench now Supports I2V Eval📢

📊 #VBench now supports the multi-dimensional evaluation of Image-to-Video (I2V) models

🏆 #DynamiCrafter and #SVD are among the top models

- Code: github.com/Vchitect/VBench
- Leaderboard Hugging Face: huggingface.co/spaces/Vchitec… . Thanks to AK!

😍😍😍

GG

Core pytorch NNs (forward and backward) written in clean, readable Triton (from @bobmcdear)
github.com/BobMcDear/atto…

AutoTrain finetuned llama3 beats the base instruct model on all but one benchmark on the open llm leaderboard 🚀 This model was finetuned using ORPO and is also publicly available. No code was written and all the setup took less than 10mins. 🤗 `pip install autotrain-advanced`

This video from Umer Adil is *the* best resource I've seen for learning OpenAI Triton -- and one of the best deep tech tutorials of any kind I've seen.
youtube.com/watch?v=DdTsX6…

The last natural step

Python kullanarak üretim bandındaki kırmızı renkli şişeleri sayan bir proje yaptım. Görüntü işleri teknikleri kullandığım için ortalama 70 FPS aldım. Kodları GitHub hesabımda paylaştım.
Aşağıdaki linkten ulaşabilirsiniz

github.com/Deepandreinfor…

Excited to share Penzai, a JAX research toolkit from Google DeepMind for building, editing, and visualizing neural networks! Penzai makes it easy to see model internals and lets you inject custom logic anywhere.

Check it out on GitHub: github.com/google-deepmin…

New attention masking nodes will drop soon! They make it super easy to mix even very different subjects and styles in the same composition in just one generation

New multimodal dataset by xAI 🏄🏻‍♀️

uploaded by Haotian Liu (first author of the beloved LLaVA)
huggingface.co/datasets/xai-o…