Block swapping is supported for Wan, HunyuanVideo, Flux, and Chroma. Big thanks to @kohya-ss and Musubi Tuner from which most of the implementation is taken. See the example hunyuan_video.toml file ...
The development of large language models (LLMs) is entering a pivotal phase with the emergence of diffusion-based architectures. These models, spearheaded by Inception Labs through its new Mercury ...
Abstract: Single-image 3D shape reconstruction has attracted significant attention with the advance of generative models. Recent studies have utilized diffusion models to achieve unprecedented shape ...
On Thursday, Inception Labs released Mercury Coder, a new AI language model that uses diffusion techniques to generate text faster than conventional models. Unlike traditional models that create ...
Stable Diffusion is a text-to-image model which uses the power of generative AI to create realistic visuals from natural language prompts. Available through web apps, it’s an intuitive way to ...
Abstract: Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback