Add LightX2V + Wan2.2-TI2V-5B-Turbo GGUF experiment

Browse Source

Benchmarks the dense 5B Turbo model (Q8_0 GGUF + fp8 T5) as a
lower-VRAM alternative to the 14B MoE pipeline. Includes dtype
patches for dense WanModel, Wan 2.2 VAE config (48 channels, 16x
spatial), and Blackwell fp8 workaround.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

...

This commit is contained in:

Brian

2026-04-16 01:27:45 -04:00

parent 56923ff424

commit 9debc56137

8 changed files with 407 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

third_party/MuseTalk

Vendored Submodule

+1

Submodule third_party/MuseTalk added at ca5b7a8f28