diffusers/pr_11739/en/api/models/qwenimage_transformer2d.md

QwenImageTransformer2DModel

The model can be loaded with the following code snippet.

from diffusers import QwenImageTransformer2DModel

transformer = QwenImageTransformer2DModel.from_pretrained("Qwen/QwenImage-20B", subfolder="transformer", torch_dtype=torch.bfloat16)

QwenImageTransformer2DModel[[diffusers.QwenImageTransformer2DModel]]

diffusers.QwenImageTransformer2DModel[[diffusers.QwenImageTransformer2DModel]]

Source

The Transformer model introduced in Qwen.

forwarddiffusers.QwenImageTransformer2DModel.forwardhttps://github.com/huggingface/diffusers/blob/vr_11739/src/diffusers/models/transformers/transformer_qwenimage.py#L743[{"name": "hidden_states", "val": ": Tensor"}, {"name": "encoder_hidden_states", "val": ": Tensor = None"}, {"name": "encoder_hidden_states_mask", "val": ": Tensor = None"}, {"name": "timestep", "val": ": LongTensor = None"}, {"name": "img_shapes", "val": ": typing.Optional[typing.List[typing.Tuple[int, int, int]]] = None"}, {"name": "txt_seq_lens", "val": ": typing.Optional[typing.List[int]] = None"}, {"name": "guidance", "val": ": Tensor = None"}, {"name": "attention_kwargs", "val": ": typing.Optional[typing.Dict[str, typing.Any]] = None"}, {"name": "controlnet_block_samples", "val": " = None"}, {"name": "additional_t_cond", "val": " = None"}, {"name": "return_dict", "val": ": bool = True"}]- hidden_states (torch.Tensor of shape (batch_size, image_sequence_length, in_channels)) -- Input hidden_states.

• encoder_hidden_states (torch.Tensor of shape (batch_size, text_sequence_length, joint_attention_dim)) -- Conditional embeddings (embeddings computed from the input conditions such as prompts) to use.
• encoder_hidden_states_mask (torch.Tensor of shape (batch_size, text_sequence_length)) -- Mask of the input conditions.
• timestep ( torch.LongTensor) -- Used to indicate denoising step.
• attention_kwargs (dict, optional) -- A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
• return_dict (bool, optional, defaults to True) -- Whether or not to return a ~models.transformer_2d.Transformer2DModelOutput instead of a plain tuple.0If return_dict is True, an ~models.transformer_2d.Transformer2DModelOutput is returned, otherwise a tuple where the first element is the sample tensor.

The QwenTransformer2DModel forward method.

Parameters:

patch_size (int, defaults to 2) : Patch size to turn the input data into small patches.

in_channels (int, defaults to 64) : The number of channels in the input.

out_channels (int, optional, defaults to None) : The number of channels in the output. If not specified, it defaults to in_channels.

num_layers (int, defaults to 60) : The number of layers of dual stream DiT blocks to use.

attention_head_dim (int, defaults to 128) : The number of dimensions to use for each attention head.

num_attention_heads (int, defaults to 24) : The number of attention heads to use.

joint_attention_dim (int, defaults to 3584) : The number of dimensions to use for the joint attention (embedding/channel dimension of encoder_hidden_states).

guidance_embeds (bool, defaults to False) : Whether to use guidance embeddings for guidance-distilled variant of the model.

axes_dims_rope (Tuple[int], defaults to (16, 56, 56)) : The dimensions to use for the rotary positional embeddings.

Returns:

If return_dict is True, an ~models.transformer_2d.Transformer2DModelOutput is returned, otherwise a tuple where the first element is the sample tensor.

Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

diffusers.models.modeling_outputs.Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

Source

The output of Transformer2DModel.

Parameters:

sample (torch.Tensor of shape (batch_size, num_channels, height, width) or (batch size, num_vector_embeds - 1, num_latent_pixels) if Transformer2DModel is discrete) : The hidden states output conditioned on the encoder_hidden_states input. If discrete, returns probability distributions for the unnoised latent pixels.