What was the quantization process?

by LeechKing - opened 6 days ago

I attempted quantize ltx2.3-10Eros from bf16 to INT8_convrot with your node using the "on the fly quantization"
Which came out with different weights and noticeably worser in quality

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment