Add LightX2V + Wan2.2-TI2V-5B-Turbo GGUF experiment
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:
1 parent
56923ff424
commit
9debc56137
8 files changed
+407
No files matched your search
+1
Submodule third_party/MuseTalk added at ca5b7a8f28.
Reference in new issue
Block a user