wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-10 08:27:13 +08:00
Code Issues Actions 31 Packages Projects Releases Wiki Activity

Fix qwen3vl reference images when used as a text encode models. (#14845)

Browse Source 
Should not affect use as a text generation model.
This commit is contained in:
comfyanonymous 2026-07-08 22:50:25 -07:00 committed by GitHub
parent 55a15f87ce
commit d0008a8958
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
comfy/text_encoders/qwen3vl.py
View File

@ -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):