JettHu/ComfyUI_TGate

T-GATE implementation for ComfyUI.

47
/ 100
Emerging

Implements attention output caching during the later diffusion steps to reduce computation, supporting CNN-based U-Net, Transformer, and consistency models with configurable cache strategies (cross-attention only or including self-attention). Native integration via custom nodes that hook into ComfyUI's sampling pipeline without requiring git patches, with optional CPU caching for multi-batch workflows like AnimateDiff.

102 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

102

Forks

11

Language

Python

License

GPL-3.0

Last pushed

Jan 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JettHu/ComfyUI_TGate"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.