V1-5-pruned-emaonly-fp16 < NEWEST • 2025 >

This part of the name often causes the most confusion. EMA stands for .

Result: The model shrank. It lost 30% of its bulk but kept 99.9% of its artistic skill. Suddenly, it could fit into smaller memory spaces. v1-5-pruned-emaonly-fp16

The "emaonly" tag indicates that the non-EMA weights have been stripped out of the file entirely. By keeping only the EMA weights, the file size is roughly halved. While the filename implies it is "EMA only," this version is generally considered the "standard" inference model because it offers the best balance of quality and size. This part of the name often causes the most confusion

When a neural network is trained, the resulting file (checkpoint) often contains data that is useful for further training but unnecessary for simply generating images. In the context of AI models, "pruning" refers to the removal of redundant weights or unused data branches. It lost 30% of its bulk but kept 99

In standard Stable Diffusion v1.5 checkpoints, the file contains both sets. However, when generating images, the raw non-EMA weights are generally considered inferior to the EMA weights.