[Feature] [HunyuanImage3] Add TeaCache support for inference acceleration (#1927)

Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
This commit is contained in:
Ding Zuhaoand汪志鹏 authored and GitHub committed 2026-03-28 15:24:21 +00:00
1 parent a3e1322ad9
commit 283a62fd76
4 files changed
+89 -11

No files matched your search

+10
View File
@@ -54,6 +54,16 @@ _MODEL_COEFFICIENTS = {
-12.281286412689623,
1.0733905006198015,
],
# HunyuanImage3 pipeline coefficients
# Calibrated via polyfit on 3920 data points (80 prompts × 49 steps).
# Maps time_embed rel_l1 (range ~0.12-0.54) to output rel_l1 (range ~0.01-0.53).
"HunyuanImage3Pipeline": [
1.04117826e02,
-1.26848482e02,
5.68168652e01,
-1.04182570e01,
6.78098549e-01,
],
}