Diffusers documentation
ErnieImageTransformer2DModel
You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v0.39.0).
ErnieImageTransformer2DModel
A Transformer model for image-like data from ERNIE-Image.
A Transformer model for image-like data from ERNIE-Image-Turbo.
ErnieImageTransformer2DModel
class diffusers.ErnieImageTransformer2DModel
< source >( hidden_size: int = 3072num_attention_heads: int = 24num_layers: int = 24ffn_hidden_size: int = 8192in_channels: int = 128out_channels: int = 128patch_size: int = 1text_in_dim: int = 2560rope_theta: int = 256rope_axes_dim: typing.Tuple[int, int, int] = (32, 48, 48)eps: float = 1e-06qk_layernorm: bool = True )
forward
< source >( hidden_states: Tensortimestep: Tensortext_bth: Tensortext_lens: Tensorreturn_dict: bool = True )
Parameters
- hidden_states (
torch.Tensorof shape(batch_size, in_channels, height, width)) — Inputhidden_states. - timestep (
torch.LongTensor) — Used to indicate denoising step. - text_bth (
torch.Tensor) — Conditional text embeddings (embeddings computed from the input conditions such as prompts) to use, shaped(batch_size, text_length, embed_dims). - text_lens (
torch.Tensor) — Per-sample text sequence lengths used to build the attention mask. - return_dict (
bool, optional, defaults toTrue) — Whether or not to return a~models.transformer_2d.Transformer2DModelOutputinstead of a plain tuple.
The ErnieImageTransformer2DModel forward method.