Apple researchers develop STARFlow, a breakthrough AI image generation system that challenges diffusion models used by DALL-E and Midjourney with competitive performance.

This important study presents a compelling theoretical framework for understanding phase separation of membrane-bound proteins, with a focus on the organization of tight junction components. By ...

🔥 Generative frame interpolation / looping video generation model weights (320x512 ... domain still images based on text prompt by leveraging the pre-trained video diffusion priors. Please check our ...

9b01873. Supporting information contains additional data, further discussions of the exchange model, calculations of the water domain thickness, and a plot of diffusion coefficients versus domain ...

Driven by the diffusion model-based learning approach, AIGN has great potential to learn the reward-maximizing trajectories, automatically satisfy multiple constraints, adapt to different objectives ...

(1) We released the 50 diffusion steps model (instead of 1000 steps) which runs 20X faster with comparable results. (2) Calling CLIP just once and caching the result runs 2X faster for all models.

Upgrades to python 3.9, and adds support for NVIDIA 50xx series (Blackwell) GPUs. Adds support for AMD GPUs, as well as integrated GPUs on Windows.

Google previewed a new AI model, Gemini Diffusion, that it claims is “state-of-the-art” on certain coding and math tasks — leveraging parallel generation to achieve low latency.

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An ...

which was trained as a standard noise-prediction model on 512x512 images and is also made available. Added a x4 upscaling latent text-guided diffusion model. A text-guided inpainting model, finetuned ...