AI News Pulse

Research

WeChat unveils WeLM-Image, a unified image generation and editing model

WeLM-Image has 31.7B stored parameters with about 5.4B active per generated token and is designed for single-GPU deployment. Its Turbo variant generates a 1024x1024 image in 4.98 seconds on one NVIDIA H20 using eight steps, per the paper's reported results.

1outlet ran itRead at Hugging Face Papers
Status
Research
Published
That day
Outlets
1
Written by
Claude How

Every outlet that ran it 1 article

All news