From d0008a8958b9170b7eb1e4d5e45bff95249f36ee Mon Sep 17 00:00:00 2001
From: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
Date: Wed, 8 Jul 2026 22:50:25 -0700
Subject: [PATCH] Fix qwen3vl reference images when used as a text encode
 models. (#14845)

Should not affect use as a text generation model.
---
 comfy/text_encoders/qwen3vl.py | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/comfy/text_encoders/qwen3vl.py b/comfy/text_encoders/qwen3vl.py
index 2082c42e7..7a329d2d6 100644
--- a/comfy/text_encoders/qwen3vl.py
+++ b/comfy/text_encoders/qwen3vl.py
@@ -90,6 +90,27 @@ class Qwen3VL(BaseLlama, BaseQwen3, BaseGenerate, torch.nn.Module):
                 deepstack = [torch.cat([deepstack[i], ds[i]], dim=0) for i in range(len(ds))]
         return position_ids, visual_pos_masks, deepstack
 
+    def forward(self, input_ids, attention_mask=None, embeds=None, num_tokens=None, intermediate_output=None, final_layer_norm_intermediate=True, dtype=None, embeds_info=[], **kwargs):
+        position_ids = kwargs.pop("position_ids", None)
+        visual_pos_masks = kwargs.pop("visual_pos_masks", None)
+        deepstack_embeds = kwargs.pop("deepstack_embeds", None)
+        if embeds is not None and position_ids is None:
+            position_ids, visual_pos_masks, deepstack_embeds = self.build_image_inputs(embeds, embeds_info)
+        return self.model(
+            input_ids,
+            attention_mask=attention_mask,
+            embeds=embeds,
+            num_tokens=num_tokens,
+            intermediate_output=intermediate_output,
+            final_layer_norm_intermediate=final_layer_norm_intermediate,
+            dtype=dtype,
+            position_ids=position_ids,
+            embeds_info=embeds_info,
+            visual_pos_masks=visual_pos_masks,
+            deepstack_embeds=deepstack_embeds,
+            **kwargs,
+        )
+
 
 def _make_qwen3vl_model(model_type):
     class Qwen3VL_(Qwen3VL):