This is an FP8 quantized version of the original LongCat-Image-Edit model developed by Meituan⚡ Operational Purpose:

VRAM Reduction: Drastically lowers memory consumption, allowing you to run the model on standard consumer hardware.
Faster Inference: Accelerates image processing speeds while maintaining the structural integrity of the original model.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support