From 745b6beb3d0b0f9392539f3def0142a268989d3d Mon Sep 17 00:00:00 2001
From: laurigates <13014001+laurigates@users.noreply.github.com>
Date: Thu, 7 May 2026 14:53:55 +0300
Subject: [PATCH] fix: return 3-tuple from predict_with_cfg use_zero_init
 early-exit

The CFG-Zero* early-exit path returned a 2-tuple while every
caller (and every other return in predict_with_cfg) unpacks 3
values: (noise_pred, noise_pred_ovi, cache_state). Workflows that
enable both cfg_zero_star and use_zero_init crash on step 0 with
"ValueError: not enough values to unpack (expected 3, got 2)".

Pass cache_state through unchanged - at the zero-init step there
is no cache update to record, so returning the input cache state
is the natural identity.

Same shape of bug as #1454 (HUMO branch), different code path.

Fixes #2010
---
 nodes_sampler.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/nodes_sampler.py b/nodes_sampler.py
index 4dc208fe..e10d8332 100644
--- a/nodes_sampler.py
+++ b/nodes_sampler.py
@@ -1176,7 +1176,7 @@ def predict_with_cfg(z, cfg_scale, positive_embeds, negative_embeds, timestep, i
             with torch.autocast(device_type=mm.get_autocast_device(device), dtype=dtype) if autocast_enabled else nullcontext():
 
                 if use_cfg_zero_star and (idx <= zero_star_steps) and use_zero_init:
-                    return z*0, None
+                    return z*0, None, cache_state
 
                 nonlocal patcher
                 current_step_percentage = idx / len(timesteps)