Diffusers 文件
FluxTransformer2DModel
並獲得增強的文件體驗
開始使用
FluxTransformer2DModel
來自 Flux 的影像類資料的 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) )
引數
- patch_size (
int, 預設為1) — 用於將輸入資料分成小塊的塊大小。 - in_channels (
int, 預設為64) — 輸入中的通道數。 - out_channels (
int, 可選, 預設為None) — 輸出中的通道數。如果未指定，則預設為in_channels。 - num_layers (
int, 預設為19) — 要使用的雙流 DiT 塊層數。 - num_single_layers (
int, 預設為38) — 要使用的單流 DiT 塊層數。 - attention_head_dim (
int, 預設為128) — 每個注意力頭的維度。 - num_attention_heads (
int, 預設為24) — 要使用的注意力頭數。 - joint_attention_dim (
int, 預設為4096) — 用於聯合注意力（encoder_hidden_states的嵌入/通道維度）的維度數。 - pooled_projection_dim (
int, 預設為768) — 用於池化投影的維度數。 - guidance_embeds (
bool, 預設為False) — 是否對模型的指導蒸餾變體使用指導嵌入。 - axes_dims_rope (
Tuple[int], 預設為(16, 56, 56)) — 用於旋轉位置嵌入的維度。
Flux 中引入的 Transformer 模型。
參考：https://blackforestlabs.ai/announcing-black-forest-labs/
前向傳播
< 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 )
引數
- hidden_states (
torch.Tensor，形狀為(batch_size, image_sequence_length, in_channels)) — 輸入hidden_states。 - encoder_hidden_states (
torch.Tensor，形狀為(batch_size, text_sequence_length, joint_attention_dim)) — 要使用的條件嵌入（從提示等輸入條件計算的嵌入）。 - pooled_projections (
torch.Tensor，形狀為(batch_size, projection_dim)) — 從輸入條件的嵌入投影的嵌入。 - timestep (
torch.LongTensor) — 用於指示去噪步驟。 - block_controlnet_hidden_states — (
listoftorch.Tensor): 如果指定，將新增到變壓器塊殘差中的張量列表。 - joint_attention_kwargs (
dict, 可選) — 如果指定，將傳遞給 diffusers.models.attention_processor 中self.processor定義的AttentionProcessor的 kwargs 字典。 - return_dict (
bool, 可選, 預設為True) — 是否返回~models.transformer_2d.Transformer2DModelOutput而不是普通元組。
FluxTransformer2DModel 的 forward 方法。
啟用融合 QKV 投影。對於自注意力模組，所有投影矩陣（即查詢、鍵、值）都將融合。對於交叉注意力模組，鍵和值投影矩陣將融合。
此 API 是 🧪 實驗性的。
設定注意力處理器
< 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]]] )
設定用於計算注意力的注意力處理器。