Publish DiffusionKit format checkpoints for FLUX
atiorh opened this issue · 2 comments
atiorh commented
DiffusionKit currently patches the original FLUX checkpoint here each time the weights are restored. We should publish pre-patched checkpoints to avoid runtime reformatting.
atiorh commented
@arda-argmax Feel free to close this issue by posting your latency stats.
arda-argmax commented
INFO:diffusionkit.mlx.model_io:Time to create model: 0.008893251419067383 s
INFO:diffusionkit.mlx.model_io:Time to load weights: 0.3058888912200928 s
INFO:diffusionkit.mlx.model_io:Time to adjust weights: 0.007555961608886719 s
Patching the checkpoint takes around 10 ms, which does not create significant latency.