diffusers/pr_12595/en/api/models/lumina_nextdit2d.md

LuminaNextDiT2DModel

A Next Version of Diffusion Transformer model for 2D data from Lumina-T2X.

LuminaNextDiT2DModel[[diffusers.LuminaNextDiT2DModel]]

class diffusers.LuminaNextDiT2DModeldiffusers.LuminaNextDiT2DModelhttps://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/lumina_nextdit2d.py#L178[{"name": "sample_size", "val": ": int = 128"}, {"name": "patch_size", "val": ": typing.Optional[int] = 2"}, {"name": "in_channels", "val": ": typing.Optional[int] = 4"}, {"name": "hidden_size", "val": ": typing.Optional[int] = 2304"}, {"name": "num_layers", "val": ": typing.Optional[int] = 32"}, {"name": "num_attention_heads", "val": ": typing.Optional[int] = 32"}, {"name": "num_kv_heads", "val": ": typing.Optional[int] = None"}, {"name": "multiple_of", "val": ": typing.Optional[int] = 256"}, {"name": "ffn_dim_multiplier", "val": ": typing.Optional[float] = None"}, {"name": "norm_eps", "val": ": typing.Optional[float] = 1e-05"}, {"name": "learn_sigma", "val": ": typing.Optional[bool] = True"}, {"name": "qk_norm", "val": ": typing.Optional[bool] = True"}, {"name": "cross_attention_dim", "val": ": typing.Optional[int] = 2048"}, {"name": "scaling_factor", "val": ": typing.Optional[float] = 1.0"}]- sample_size (int) -- The width of the latent images. This is fixed during training since it is used to learn a number of position embeddings.

• patch_size (int, optional, (int, optional, defaults to 2) -- The size of each patch in the image. This parameter defines the resolution of patches fed into the model.
• in_channels (int, optional, defaults to 4) -- The number of input channels for the model. Typically, this matches the number of channels in the input images.
• hidden_size (int, optional, defaults to 4096) -- The dimensionality of the hidden layers in the model. This parameter determines the width of the model's hidden representations.
• num_layers (int, optional, default to 32) -- The number of layers in the model. This defines the depth of the neural network.
• num_attention_heads (int, optional, defaults to 32) -- The number of attention heads in each attention layer. This parameter specifies how many separate attention mechanisms are used.
• num_kv_heads (int, optional, defaults to 8) -- The number of key-value heads in the attention mechanism, if different from the number of attention heads. If None, it defaults to num_attention_heads.
• multiple_of (int, optional, defaults to 256) -- A factor that the hidden size should be a multiple of. This can help optimize certain hardware configurations.
• ffn_dim_multiplier (float, optional) -- A multiplier for the dimensionality of the feed-forward network. If None, it uses a default value based on the model configuration.
• norm_eps (float, optional, defaults to 1e-5) -- A small value added to the denominator for numerical stability in normalization layers.
• learn_sigma (bool, optional, defaults to True) -- Whether the model should learn the sigma parameter, which might be related to uncertainty or variance in predictions.
• qk_norm (bool, optional, defaults to True) -- Indicates if the queries and keys in the attention mechanism should be normalized.
• cross_attention_dim (int, optional, defaults to 2048) -- The dimensionality of the text embeddings. This parameter defines the size of the text representations used in the model.
• scaling_factor (float, optional, defaults to 1.0) -- A scaling factor applied to certain parameters or layers in the model. This can be used for adjusting the overall scale of the model's operations.0

LuminaNextDiT: Diffusion model with a Transformer backbone.

Inherit ModelMixin and ConfigMixin to be compatible with the sampler StableDiffusionPipeline of diffusers.

forwarddiffusers.LuminaNextDiT2DModel.forwardhttps://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/lumina_nextdit2d.py#L291[{"name": "hidden_states", "val": ": Tensor"}, {"name": "timestep", "val": ": Tensor"}, {"name": "encoder_hidden_states", "val": ": Tensor"}, {"name": "encoder_mask", "val": ": Tensor"}, {"name": "image_rotary_emb", "val": ": Tensor"}, {"name": "cross_attention_kwargs", "val": ": typing.Dict[str, typing.Any] = None"}, {"name": "return_dict", "val": " = True"}]- hidden_states (torch.Tensor) -- Input tensor of shape (N, C, H, W).

• timestep (torch.Tensor) -- Tensor of diffusion timesteps of shape (N,).
• encoder_hidden_states (torch.Tensor) -- Tensor of caption features of shape (N, D).
• encoder_mask (torch.Tensor) -- Tensor of caption masks of shape (N, L).0

Forward pass of LuminaNextDiT.