Skip to content

0.18.38-CV

Choose a tag to compare

View all tags
@fxd0h fxd0h released this 08 Aug 17:00
· 11 commits to main since this release
v.0.18.38-CV
768fbfb

Fixes

  • Qwen-Image 4-bit no longer accumulates quantization noise across steps (upstream #484): at uniform q4, more steps made output grainier, not better (flat-field sigma 5.06 to 16.07 from 4 to 50 steps on Qwen-Image-2512). Bisection traced the whole effect to the adaLN modulation producers: -q 4 now keeps the 60 img_mod_linear layers at 8-bit (~1.8 GB extra), restoring the global-q8 noise floor exactly (sigma 1.10/1.37 at 20/50 steps vs 1.15/1.31 for full q8). Same protected-layer choice as upstream #420, so saves interoperate; qwen-edit and qwen-image-flash inherit the fix. Stored quantized models now reconstruct at the exact per-layer bits and group size inferred from the saved shapes, so mixed saves round-trip pixel-identically and uniform saves load exactly as before. (#60)

Full details in the CHANGELOG.

Assets 4
Loading