Diffusers 文档
HunyuanVideoTransformer3DModel
并获得增强的文档体验
开始使用
HunyuanVideoTransformer3DModel
在腾讯的 HunyuanVideo: 大型视频生成模型的系统框架 中，介绍了一种用于 3D 视频类数据的扩散 Transformer 模型。
该模型可以使用以下代码片段加载。
from diffusers import HunyuanVideoTransformer3DModel
transformer = HunyuanVideoTransformer3DModel.from_pretrained("hunyuanvideo-community/HunyuanVideo", subfolder="transformer", torch_dtype=torch.bfloat16)HunyuanVideoTransformer3DModel
class diffusers.HunyuanVideoTransformer3DModel
< source >( in_channels: int = 16 out_channels: int = 16 num_attention_heads: int = 24 attention_head_dim: int = 128 num_layers: int = 20 num_single_layers: int = 40 num_refiner_layers: int = 2 mlp_ratio: float = 4.0 patch_size: int = 2 patch_size_t: int = 1 qk_norm: str = 'rms_norm' guidance_embeds: bool = True text_embed_dim: int = 4096 pooled_projection_dim: int = 768 rope_theta: float = 256.0 rope_axes_dim: typing.Tuple[int] = (16, 56, 56) )
参数
- in_channels (
int, 默认为16) — 输入中的通道数。 - out_channels (
int, 默认为16) — 输出中的通道数。 - num_attention_heads (
int, 默认为24) — 用于多头注意力的头的数量。 - attention_head_dim (
int, 默认为128) — 每个头中的通道数。 - num_layers (
int, 默认为20) — 要使用的双流块的层数。 - num_single_layers (
int, 默认为40) — 要使用的单流块的层数。 - num_refiner_layers (
int, 默认为2) — 要使用的精炼器块的层数。 - mlp_ratio (
float, 默认为4.0) — 前馈网络中隐藏层大小与输入大小的比率。 - patch_size (
int, 默认为2) — 在 patch embedding 层中使用的空间 patch 的大小。 - patch_size_t (
int, 默认为1) — 在 patch 嵌入层中使用的时序 patch 的大小。 - qk_norm (
str, 默认为rms_norm) — 用于注意力层中 query 和 key 投影的归一化方法。 - guidance_embeds (
bool, 默认为True) — 是否在模型中使用引导 embeddings。 - text_embed_dim (
int, 默认为4096) — 来自文本编码器的文本 embeddings 的输入维度。 - pooled_projection_dim (
int, 默认为768) — 文本 embeddings 的池化投影的维度。 - rope_theta (
float, 默认为256.0) — RoPE 层中使用的 theta 值。 - rope_axes_dim (
Tuple[int], 默认为(16, 56, 56)) — RoPE 层中使用的轴的维度。
用于 HunyuanVideo 中的类视频数据的 Transformer 模型。
set_attn_processor
< 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 processor。
Transformer2DModelOutput
class diffusers.models.modeling_outputs.Transformer2DModelOutput
< source >( sample: torch.Tensor )
参数
- sample (形状为
(batch_size, num_channels, height, width)的torch.Tensor，或者如果 Transformer2DModel 是离散的，则形状为(batch size, num_vector_embeds - 1, num_latent_pixels)) — 以encoder_hidden_states输入为条件的隐藏状态输出。 如果是离散的，则返回未噪声化的潜在像素的概率分布。
Transformer2DModel 的输出。