mmagic.models.archs.attention_injection¶ Module Contents¶ Classes¶ AttentionInjection Wrapper for stable diffusion unet. Functions¶ torch_dfs(model) Attributes¶ AttentionStatus mmagic.models.archs.attention_injection.AttentionStatus[source]¶ mmagic.models.archs.attention_injection.torch_dfs(model: torch.nn.Module)[source]¶ class mmagic.models.archs.attention_injection.AttentionInjection(module: torch.nn.Module, injection_weight=5)[source]¶ Bases: torch.nn.Module Wrapper for stable diffusion unet. Parameters module (nn.Module) – The module to be wrapped. forward(x: torch.Tensor, t, encoder_hidden_states=None, down_block_additional_residuals=None, mid_block_additional_residual=None, ref_x=None) → torch.Tensor[source]¶ Forward and add LoRA mapping. Parameters x (Tensor) – The input tensor. Returns The output tensor. Return type Tensor