Hugging Face's logo

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 (v0.42.1).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

ErnieImageTransformer2DModel

Model Transformer untuk data seperti gambar dari ERNIE-Image.

Model Transformer untuk data seperti gambar dari ERNIE-Image-Turbo.

ErnieImageTransformer2DModel

kelas diffusers.ErnieImageTransformer2DModel

< >

( 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

< >

( hidden_states: Tensortimestep: Tensortext_bth: Tensortext_lens: Tensorreturn_dict: bool = True )

Parameter

  • hidden_states (torch.Tensor dengan bentuk (batch_size, in_channels, height, width)) — hidden_states masukan.
  • timestep (torch.LongTensor) — Digunakan untuk menunjukkan langkah denoising.
  • text_bth (torch.Tensor) — Embedding teks kondisional (embedding yang dihitung dari kondisi input seperti prompt) yang akan digunakan, dengan bentuk (batch_size, text_length, embed_dims).
  • text_lens (torch.Tensor) — Panjang sekuens teks per sampel yang digunakan untuk membangun attention mask.
  • return_dict (bool, opsional, default True) — Apakah akan mengembalikan ~models.transformer_2d.Transformer2DModelOutput alih-alih tuple biasa.

Metode forward dari ErnieImageTransformer2DModel.

Update on GitHub

←EasyAnimateTransformer3DModel Flux2Transformer2DModel→