theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1275 from Mr-Neutr0n/fix-dit-none-check

Browse Source 
Fix AttributeError when pipe.dit is None during split training
This commit is contained in:
Zhongjie Duan
2026-03-02 10:25:11 +08:00
committed by GitHub
parent ff4be1c7c7 6383ec358c
commit 29cd5c7612
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
diffsynth/pipelines/z_image.py
View File

@@ -299,7 +299,7 @@ class ZImageUnit_PromptEmbedder(PipelineUnit):
def process(self, pipe: ZImagePipeline, prompt, edit_image): def process(self, pipe: ZImagePipeline, prompt, edit_image):
pipe.load_models_to_device(self.onload_model_names) pipe.load_models_to_device(self.onload_model_names)
if hasattr(pipe, "dit") and pipe.dit.siglip_embedder is not None: if hasattr(pipe, "dit") and pipe.dit is not None and pipe.dit.siglip_embedder is not None:
# Z-Image-Turbo and Z-Image-Omni-Base use different prompt encoding methods. # Z-Image-Turbo and Z-Image-Omni-Base use different prompt encoding methods.
# We determine which encoding method to use based on the model architecture. # We determine which encoding method to use based on the model architecture.
# If you are using two-stage split training, # If you are using two-stage split training,