From 12a22083db0f1c73adc3e6ba01c5c1d7a5fe989c Mon Sep 17 00:00:00 2001
From: Wagner Bruna <wbruna@yahoo.com>
Date: Sat, 24 Oct 2026 16:59:37 -0300
Subject: [PATCH] fix: skip reference image VAE encoding when latents have no
 consumer

This could cause a crash with e.g. vlm_use_vae_input=false and
odd-sized images.
---
 src/pipeline/image.cpp | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/src/pipeline/image.cpp b/src/pipeline/image.cpp
index 38ca95c0c8..089ff63eb5 100644
--- a/src/pipeline/image.cpp
+++ b/src/pipeline/image.cpp
@@ -274,9 +274,13 @@ namespace sd::pipeline {
             LOG_INFO("EDIT mode");
         }
 
+        bool skip_vae_encoding = (sd->version == VERSION_HIDREAM_O1) || !(
+            ref_image_params.pass_to_dit || ref_image_params.vlm_use_vae_input ||
+            sd_version_is_unet_edit(sd->version) || sd_version_is_pid(sd->version));
+
         std::vector<sd::Tensor<float>> ref_latents;
         for (size_t i = 0; i < ref_images.size(); i++) {
-            if (sd->version == VERSION_HIDREAM_O1) {
+            if (skip_vae_encoding) {
                 continue;
             }
             sd::Tensor<float> ref_latent;