24 upvotes
WeLM-Image unifies text-to-image and editing on a single GPU
What is WeLM-Image: A Unified Image Generation Model towards Visual Intelligence?
WeLM-Image is an image generation model that can create pictures from text, edit images based on instructions, and blend multiple reference images, all with a single GPU. It combines language and visual understanding to support a range of tasks in one system.
Who it is for
Developers building chat or social apps can use it to add on-device image creation and editing without massive hardware.
How to try it
Open the Hugging Face Space at https://huggingface.co/spaces/WeChatAI/WeLM-Image