Diffusers 文档
一致性解码器
并获得增强的文档体验
开始使用
一致性解码器
一致性解码器可以用于解码 StableDiffusionPipeline 中去噪 UNet 的潜在表示。此解码器在 DALL-E 3 技术报告 中被引入。
原始代码库可以在 openai/consistencydecoder 找到。
目前仅支持 2 次迭代的推理。
如果没有来自 这个 issue 的 madebyollin 和 mrsteyk 的帮助，pipeline 将无法贡献。
ConsistencyDecoderVAE
class diffusers.ConsistencyDecoderVAE
< source >( scaling_factor: float = 0.18215 latent_channels: int = 4 sample_size: int = 32 encoder_act_fn: str = 'silu' encoder_block_out_channels: typing.Tuple[int, ...] = (128, 256, 512, 512) encoder_double_z: bool = True encoder_down_block_types: typing.Tuple[str, ...] = ('DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D') encoder_in_channels: int = 3 encoder_layers_per_block: int = 2 encoder_norm_num_groups: int = 32 encoder_out_channels: int = 4 decoder_add_attention: bool = False decoder_block_out_channels: typing.Tuple[int, ...] = (320, 640, 1024, 1024) decoder_down_block_types: typing.Tuple[str, ...] = ('ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D') decoder_downsample_padding: int = 1 decoder_in_channels: int = 7 decoder_layers_per_block: int = 3 decoder_norm_eps: float = 1e-05 decoder_norm_num_groups: int = 32 decoder_num_train_timesteps: int = 1024 decoder_out_channels: int = 6 decoder_resnet_time_scale_shift: str = 'scale_shift' decoder_time_embedding_type: str = 'learned' decoder_up_block_types: typing.Tuple[str, ...] = ('ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D') )
与 DALL-E 3 一致性解码器一起使用。
示例
>>> import torch
>>> from diffusers import StableDiffusionPipeline, ConsistencyDecoderVAE
>>> vae = ConsistencyDecoderVAE.from_pretrained("openai/consistency-decoder", torch_dtype=torch.float16)
>>> pipe = StableDiffusionPipeline.from_pretrained(
... "runwayml/stable-diffusion-v1-5", vae=vae, torch_dtype=torch.float16
... ).to("cuda")
>>> image = pipe("horse", generator=torch.manual_seed(0)).images[0]
>>> image禁用切片 VAE 解码。如果之前启用了 enable_slicing，此方法将恢复为单步计算解码。
禁用平铺 VAE 解码。如果之前启用了 enable_tiling，此方法将恢复为单步计算解码。
启用切片 VAE 解码。启用此选项后，VAE 将输入张量分割成切片，以分步计算解码。这有助于节省一些内存并允许更大的批处理大小。
启用平铺VAE解码。 启用此选项后，VAE会将输入张量拆分为图块，以分步计算解码和编码。 这对于节省大量内存并允许处理更大的图像非常有用。
forward
< source >( sample: Tensor sample_posterior: bool = False return_dict: bool = True generator: typing.Optional[torch._C.Generator] = None ) → DecoderOutput or tuple
参数
- sample (
torch.Tensor) — 输入样本。 - sample_posterior (
bool, optional, defaults toFalse) — 是否从后验分布中采样，默认为False。 - return_dict (
bool, optional, defaults toTrue) — 是否返回DecoderOutput而不是普通元组，默认为True。 - generator (
torch.Generator, optional, defaults toNone) — 用于采样的生成器，默认为None。
返回值
DecoderOutput 或 tuple
如果 return_dict 为 True，则返回 DecoderOutput，否则返回普通 tuple。
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]]] )
设置用于计算注意力的注意力处理器。
禁用自定义注意力处理器并设置默认的注意力实现。
tiled_encode
< source >( x: Tensor return_dict: bool = True ) → ConsistencyDecoderVAEOutput or tuple
使用平铺编码器编码一批图像。
启用此选项后，VAE会将输入张量拆分为图块，以分步计算编码。 这对于保持内存使用量恒定，而与图像大小无关非常有用。 平铺编码的最终结果与非平铺编码不同，因为每个图块都使用不同的编码器。 为了避免平铺伪影，图块会重叠并混合在一起以形成平滑的输出。 您可能仍然会在输出中看到图块大小的变化，但它们应该不那么明显。