Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Use `ErnieTEModel_` not `ErnieTEModel`. (#13431)

Bedovyyb41ab53b6f28
diff --git a/comfy/text_encoders/ernie.py b/comfy/text_encoders/ernie.py
index 2c7df78fe..46d24d222 100644
--- a/comfy/text_encoders/ernie.py
+++ b/comfy/text_encoders/ernie.py
@@ -35,4 +35,4 @@ def te(dtype_llama=None, llama_quantization_metadata=None):
model_options = model_options.copy()
model_options["quantization_metadata"] = llama_quantization_metadata
super().__init__(device=device, dtype=dtype, model_options=model_options)
- return ErnieTEModel
+ return ErnieTEModel_