Diffusers 文档
FluxTransformer2DModel
并获得增强的文档体验
开始使用
FluxTransformer2DModel
来自 Flux 的图像类数据的 Transformer 模型。
FluxTransformer2DModel
class diffusers.FluxTransformer2DModel
< source >( patch_size: int = 1 in_channels: int = 64 out_channels: typing.Optional[int] = None num_layers: int = 19 num_single_layers: int = 38 attention_head_dim: int = 128 num_attention_heads: int = 24 joint_attention_dim: int = 4096 pooled_projection_dim: int = 768 guidance_embeds: bool = False axes_dims_rope: typing.Tuple[int, int, int] = (16, 56, 56) )
参数
- patch_size (
int, 默认为1) — 用于将输入数据分成小块的块大小。 - in_channels (
int, 默认为64) — 输入中的通道数。 - out_channels (
int, 可选, 默认为None) — 输出中的通道数。如果未指定，则默认为in_channels。 - num_layers (
int, 默认为19) — 要使用的双流 DiT 块层数。 - num_single_layers (
int, 默认为38) — 要使用的单流 DiT 块层数。 - attention_head_dim (
int, 默认为128) — 每个注意力头的维度。 - num_attention_heads (
int, 默认为24) — 要使用的注意力头数。 - joint_attention_dim (
int, 默认为4096) — 用于联合注意力（encoder_hidden_states的嵌入/通道维度）的维度数。 - pooled_projection_dim (
int, 默认为768) — 用于池化投影的维度数。 - guidance_embeds (
bool, 默认为False) — 是否对模型的指导蒸馏变体使用指导嵌入。 - axes_dims_rope (
Tuple[int], 默认为(16, 56, 56)) — 用于旋转位置嵌入的维度。
Flux 中引入的 Transformer 模型。
参考：https://blackforestlabs.ai/announcing-black-forest-labs/
前向传播
< source >( hidden_states: Tensor encoder_hidden_states: Tensor = None pooled_projections: Tensor = None timestep: LongTensor = None img_ids: Tensor = None txt_ids: Tensor = None guidance: Tensor = None joint_attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None controlnet_block_samples = None controlnet_single_block_samples = None return_dict: bool = True controlnet_blocks_repeat: bool = False )
参数
- hidden_states (
torch.Tensor，形状为(batch_size, image_sequence_length, in_channels)) — 输入hidden_states。 - encoder_hidden_states (
torch.Tensor，形状为(batch_size, text_sequence_length, joint_attention_dim)) — 要使用的条件嵌入（从提示等输入条件计算的嵌入）。 - pooled_projections (
torch.Tensor，形状为(batch_size, projection_dim)) — 从输入条件的嵌入投影的嵌入。 - timestep (
torch.LongTensor) — 用于指示去噪步骤。 - block_controlnet_hidden_states — (
listoftorch.Tensor): 如果指定，将添加到变压器块残差中的张量列表。 - joint_attention_kwargs (
dict, 可选) — 如果指定，将传递给 diffusers.models.attention_processor 中self.processor定义的AttentionProcessor的 kwargs 字典。 - return_dict (
bool, 可选, 默认为True) — 是否返回~models.transformer_2d.Transformer2DModelOutput而不是普通元组。
FluxTransformer2DModel 的 forward 方法。
启用融合 QKV 投影。对于自注意力模块，所有投影矩阵（即查询、键、值）都将融合。对于交叉注意力模块，键和值投影矩阵将融合。
此 API 是 🧪 实验性的。
设置注意力处理器
< source >( processor: typing.Union[diffusers.models.attention_processor.AttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor2_0, diffusers.models.attention_processor.JointAttnProcessor2_0, diffusers.models.attention_processor.PAGJointAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGJointAttnProcessor2_0, diffusers.models.attention_processor.FusedJointAttnProcessor2_0, diffusers.models.attention_processor.AllegroAttnProcessor2_0, diffusers.models.attention_processor.AuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FusedAuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.CogVideoXAttnProcessor2_0, diffusers.models.attention_processor.FusedCogVideoXAttnProcessor2_0, diffusers.models.attention_processor.XFormersAttnAddedKVProcessor, diffusers.models.attention_processor.XFormersAttnProcessor, diffusers.models.attention_processor.XLAFlashAttnProcessor2_0, diffusers.models.attention_processor.AttnProcessorNPU, diffusers.models.attention_processor.AttnProcessor2_0, diffusers.models.attention_processor.MochiVaeAttnProcessor2_0, diffusers.models.attention_processor.MochiAttnProcessor2_0, diffusers.models.attention_processor.StableAudioAttnProcessor2_0, diffusers.models.attention_processor.HunyuanAttnProcessor2_0, diffusers.models.attention_processor.FusedHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.LuminaAttnProcessor2_0, diffusers.models.attention_processor.FusedAttnProcessor2_0, diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0, diffusers.models.attention_processor.SlicedAttnProcessor, diffusers.models.attention_processor.SlicedAttnAddedKVProcessor, diffusers.models.attention_processor.SanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleLinearAttention, diffusers.models.attention_processor.SanaMultiscaleAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleAttentionProjection, diffusers.models.attention_processor.IPAdapterAttnProcessor, diffusers.models.attention_processor.IPAdapterAttnProcessor2_0, diffusers.models.attention_processor.IPAdapterXFormersAttnProcessor, diffusers.models.attention_processor.SD3IPAdapterJointAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.LoRAAttnProcessor, diffusers.models.attention_processor.LoRAAttnProcessor2_0, diffusers.models.attention_processor.LoRAXFormersAttnProcessor, diffusers.models.attention_processor.LoRAAttnAddedKVProcessor, typing.Dict[str, typing.Union[diffusers.models.attention_processor.AttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor2_0, diffusers.models.attention_processor.JointAttnProcessor2_0, diffusers.models.attention_processor.PAGJointAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGJointAttnProcessor2_0, diffusers.models.attention_processor.FusedJointAttnProcessor2_0, diffusers.models.attention_processor.AllegroAttnProcessor2_0, diffusers.models.attention_processor.AuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FusedAuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.CogVideoXAttnProcessor2_0, diffusers.models.attention_processor.FusedCogVideoXAttnProcessor2_0, diffusers.models.attention_processor.XFormersAttnAddedKVProcessor, diffusers.models.attention_processor.XFormersAttnProcessor, diffusers.models.attention_processor.XLAFlashAttnProcessor2_0, diffusers.models.attention_processor.AttnProcessorNPU, diffusers.models.attention_processor.AttnProcessor2_0, diffusers.models.attention_processor.MochiVaeAttnProcessor2_0, diffusers.models.attention_processor.MochiAttnProcessor2_0, diffusers.models.attention_processor.StableAudioAttnProcessor2_0, diffusers.models.attention_processor.HunyuanAttnProcessor2_0, diffusers.models.attention_processor.FusedHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.LuminaAttnProcessor2_0, diffusers.models.attention_processor.FusedAttnProcessor2_0, diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0, diffusers.models.attention_processor.SlicedAttnProcessor, diffusers.models.attention_processor.SlicedAttnAddedKVProcessor, diffusers.models.attention_processor.SanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleLinearAttention, diffusers.models.attention_processor.SanaMultiscaleAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleAttentionProjection, diffusers.models.attention_processor.IPAdapterAttnProcessor, diffusers.models.attention_processor.IPAdapterAttnProcessor2_0, diffusers.models.attention_processor.IPAdapterXFormersAttnProcessor, diffusers.models.attention_processor.SD3IPAdapterJointAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.LoRAAttnProcessor, diffusers.models.attention_processor.LoRAAttnProcessor2_0, diffusers.models.attention_processor.LoRAXFormersAttnProcessor, diffusers.models.attention_processor.LoRAAttnAddedKVProcessor]]] )
设置用于计算注意力的注意力处理器。