diffusers/pr_13881/en/api/activations.md

Activation functions

Customized activation functions for supporting various models in 🤗 Diffusers.

GELU[[diffusers.models.activations.GELU]]

• dim_in (int) -- The number of channels in the input.
• dim_out (int) -- The number of channels in the output.
• approximate (str, optional, defaults to "none") -- If "tanh", use tanh approximation.
• bias (bool, defaults to True) -- Whether to use a bias in the linear layer.

GELU activation function with tanh approximation support with approximate="tanh".

GEGLU[[diffusers.models.activations.GEGLU]]

• dim_in (int) -- The number of channels in the input.
• dim_out (int) -- The number of channels in the output.
• bias (bool, defaults to True) -- Whether to use a bias in the linear layer.

A variant of the gated linear unit activation function.

ApproximateGELU[[diffusers.models.activations.ApproximateGELU]]

• dim_in (int) -- The number of channels in the input.
• dim_out (int) -- The number of channels in the output.
• bias (bool, defaults to True) -- Whether to use a bias in the linear layer.

The approximate form of the Gaussian Error Linear Unit (GELU). For more details, see section 2 of this paper.

SwiGLU[[diffusers.models.activations.SwiGLU]]

• dim_in (int) -- The number of channels in the input.
• dim_out (int) -- The number of channels in the output.
• bias (bool, defaults to True) -- Whether to use a bias in the linear layer.

A variant of the gated linear unit activation function. It's similar to GEGLU but uses SiLU / Swish instead of GeLU.

FP32SiLU[[diffusers.models.activations.FP32SiLU]]

SiLU activation function with input upcasted to torch.float32.

LinearActivation[[diffusers.models.activations.LinearActivation]]