mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2026-02-12 12:15:09 -05:00
91f91aa835
If the transformer fills up VRAM, then when we VAE encode kontext latents, we'll need to first offload the transformer (partially, if partial loading is enabled). No need to do this - we can encode kontext latents before loading the transformer to reduce model thrashing.