CalamitousFelicitousness f8bd53a96b fix(preview): keep taesd preview size constant across decode layers ...

taesd_layers < 3 drops spatial upsample blocks in the TAESD/TAEHV
decoders, shrinking preview output 2x/4x. Both UIs size the live preview
from the image's intrinsic pixel dimensions (modern via object-fit:
scale-down, standard via max(naturalWidth, 512px)), so lower layer counts
rendered the preview physically small.

Rescale the decoded preview spatially by 2^(3-layers) in
sd_vae_taesd.decode. Gated to TAESD and TAEHV, the only decoders that
honor taesd_layers; TAEM1 and Hybrid VAEs decode at full size and are left
untouched. Rank-agnostic so it covers both image (CHW) and video (TCHW)
previews, including single-frame video models used for txt2img.

2026-05-31 04:43:10 +01:00

..

sd_vae_approx.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_fal.py

RUF013 updates and formatting

2026-03-24 06:07:34 -07:00

sd_vae_natten.py

unified logger

2026-02-19 09:46:42 +01:00

sd_vae_ostris.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_remote.py

fix custom vae loader

2026-05-17 08:37:13 +02:00

sd_vae_repa.py

cleanup logger

2026-02-19 11:09:13 +01:00

sd_vae_stablecascade.py

pylint

2026-02-19 11:36:20 +01:00

sd_vae_taesd.py

fix(preview): keep taesd preview size constant across decode layers

2026-05-31 04:43:10 +01:00