ControlNetModel
The ControlNet model was introduced in Adding Conditional Control to Text-to-Image Diffusion Models by Lvmin Zhang, Anyi Rao, Maneesh Agrawala. It provides a greater degree of control over text-to-image generation by conditioning the model on additional inputs such as edge maps, depth maps, segmentation maps, and keypoints for pose detection.
The abstract from the paper is:
We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with “zero convolutions” (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning controls, eg, edges, depth, segmentation, human pose, etc, with Stable Diffusion, using single or multiple conditions, with or without prompts. We show that the training of ControlNets is robust with small (<50k) and large (>1m) datasets. Extensive results show that ControlNet may facilitate wider applications to control image diffusion models.
Loading from the original format
By default the ControlNetModel should be loaded with from_pretrained(), but it can also be loaded
from the original format using FromOriginalModelMixin.from_single_file
as follows:
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
url = "https://huggingface.co./lllyasviel/ControlNet-v1-1/blob/main/control_v11p_sd15_canny.pth" # can also be a local path
controlnet = ControlNetModel.from_single_file(url)
url = "https://huggingface.co./stable-diffusion-v1-5/stable-diffusion-v1-5/blob/main/v1-5-pruned.safetensors" # can also be a local path
pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=controlnet)
ControlNetModel
class diffusers.ControlNetModel
< source >( in_channels: int = 4 conditioning_channels: int = 3 flip_sin_to_cos: bool = True freq_shift: int = 0 down_block_types: typing.Tuple[str, ...] = ('CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D') mid_block_type: typing.Optional[str] = 'UNetMidBlock2DCrossAttn' only_cross_attention: typing.Union[bool, typing.Tuple[bool]] = False block_out_channels: typing.Tuple[int, ...] = (320, 640, 1280, 1280) layers_per_block: int = 2 downsample_padding: int = 1 mid_block_scale_factor: float = 1 act_fn: str = 'silu' norm_num_groups: typing.Optional[int] = 32 norm_eps: float = 1e-05 cross_attention_dim: int = 1280 transformer_layers_per_block: typing.Union[int, typing.Tuple[int, ...]] = 1 encoder_hid_dim: typing.Optional[int] = None encoder_hid_dim_type: typing.Optional[str] = None attention_head_dim: typing.Union[int, typing.Tuple[int, ...]] = 8 num_attention_heads: typing.Union[int, typing.Tuple[int, ...], NoneType] = None use_linear_projection: bool = False class_embed_type: typing.Optional[str] = None addition_embed_type: typing.Optional[str] = None addition_time_embed_dim: typing.Optional[int] = None num_class_embeds: typing.Optional[int] = None upcast_attention: bool = False resnet_time_scale_shift: str = 'default' projection_class_embeddings_input_dim: typing.Optional[int] = None controlnet_conditioning_channel_order: str = 'rgb' conditioning_embedding_out_channels: typing.Optional[typing.Tuple[int, ...]] = (16, 32, 96, 256) global_pool_conditions: bool = False addition_embed_type_num_heads: int = 64 )
Parameters
- in_channels (
int
, defaults to 4) — The number of channels in the input sample. - flip_sin_to_cos (
bool
, defaults toTrue
) — Whether to flip the sin to cos in the time embedding. - freq_shift (
int
, defaults to 0) — The frequency shift to apply to the time embedding. - down_block_types (
tuple[str]
, defaults to("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")
) — The tuple of downsample blocks to use. - only_cross_attention (
Union[bool, Tuple[bool]]
, defaults toFalse
) — - block_out_channels (
tuple[int]
, defaults to(320, 640, 1280, 1280)
) — The tuple of output channels for each block. - layers_per_block (
int
, defaults to 2) — The number of layers per block. - downsample_padding (
int
, defaults to 1) — The padding to use for the downsampling convolution. - mid_block_scale_factor (
float
, defaults to 1) — The scale factor to use for the mid block. - act_fn (
str
, defaults to “silu”) — The activation function to use. - norm_num_groups (
int
, optional, defaults to 32) — The number of groups to use for the normalization. If None, normalization and activation layers is skipped in post-processing. - norm_eps (
float
, defaults to 1e-5) — The epsilon to use for the normalization. - cross_attention_dim (
int
, defaults to 1280) — The dimension of the cross attention features. - transformer_layers_per_block (
int
orTuple[int]
, optional, defaults to 1) — The number of transformer blocks of typeBasicTransformerBlock
. Only relevant for~models.unet_2d_blocks.CrossAttnDownBlock2D
,~models.unet_2d_blocks.CrossAttnUpBlock2D
,~models.unet_2d_blocks.UNetMidBlock2DCrossAttn
. - encoder_hid_dim (
int
, optional, defaults to None) — Ifencoder_hid_dim_type
is defined,encoder_hidden_states
will be projected fromencoder_hid_dim
dimension tocross_attention_dim
. - encoder_hid_dim_type (
str
, optional, defaults toNone
) — If given, theencoder_hidden_states
and potentially other embeddings are down-projected to text embeddings of dimensioncross_attention
according toencoder_hid_dim_type
. - attention_head_dim (
Union[int, Tuple[int]]
, defaults to 8) — The dimension of the attention heads. - use_linear_projection (
bool
, defaults toFalse
) — - class_embed_type (
str
, optional, defaults toNone
) — The type of class embedding to use which is ultimately summed with the time embeddings. Choose from None,"timestep"
,"identity"
,"projection"
, or"simple_projection"
. - addition_embed_type (
str
, optional, defaults toNone
) — Configures an optional embedding which will be summed with the time embeddings. Choose fromNone
or “text”. “text” will use theTextTimeEmbedding
layer. - num_class_embeds (
int
, optional, defaults to 0) — Input dimension of the learnable embedding matrix to be projected totime_embed_dim
, when performing class conditioning withclass_embed_type
equal toNone
. - upcast_attention (
bool
, defaults toFalse
) — - resnet_time_scale_shift (
str
, defaults to"default"
) — Time scale shift config for ResNet blocks (seeResnetBlock2D
). Choose fromdefault
orscale_shift
. - projection_class_embeddings_input_dim (
int
, optional, defaults toNone
) — The dimension of theclass_labels
input whenclass_embed_type="projection"
. Required whenclass_embed_type="projection"
. - controlnet_conditioning_channel_order (
str
, defaults to"rgb"
) — The channel order of conditional image. Will convert torgb
if it’sbgr
. - conditioning_embedding_out_channels (
tuple[int]
, optional, defaults to(16, 32, 96, 256)
) — The tuple of output channel for each block in theconditioning_embedding
layer. - global_pool_conditions (
bool
, defaults toFalse
) — TODO(Patrick) - unused parameter. - addition_embed_type_num_heads (
int
, defaults to 64) — The number of heads to use for theTextTimeEmbedding
layer.
A ControlNet model.
forward
< source >( sample: Tensor timestep: typing.Union[torch.Tensor, float, int] encoder_hidden_states: Tensor controlnet_cond: Tensor conditioning_scale: float = 1.0 class_labels: typing.Optional[torch.Tensor] = None timestep_cond: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None added_cond_kwargs: typing.Optional[typing.Dict[str, torch.Tensor]] = None cross_attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None guess_mode: bool = False return_dict: bool = True ) → ControlNetOutput or tuple
Parameters
- sample (
torch.Tensor
) — The noisy input tensor. - timestep (
Union[torch.Tensor, float, int]
) — The number of timesteps to denoise an input. - encoder_hidden_states (
torch.Tensor
) — The encoder hidden states. - controlnet_cond (
torch.Tensor
) — The conditional input tensor of shape(batch_size, sequence_length, hidden_size)
. - conditioning_scale (
float
, defaults to1.0
) — The scale factor for ControlNet outputs. - class_labels (
torch.Tensor
, optional, defaults toNone
) — Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings. - timestep_cond (
torch.Tensor
, optional, defaults toNone
) — Additional conditional embeddings for timestep. If provided, the embeddings will be summed with the timestep_embedding passed through theself.time_embedding
layer to obtain the final timestep embeddings. - attention_mask (
torch.Tensor
, optional, defaults toNone
) — An attention mask of shape(batch, key_tokens)
is applied toencoder_hidden_states
. If1
the mask is kept, otherwise if0
it is discarded. Mask will be converted into a bias, which adds large negative values to the attention scores corresponding to “discard” tokens. - added_cond_kwargs (
dict
) — Additional conditions for the Stable Diffusion XL UNet. - cross_attention_kwargs (
dict[str]
, optional, defaults toNone
) — A kwargs dictionary that if specified is passed along to theAttnProcessor
. - guess_mode (
bool
, defaults toFalse
) — In this mode, the ControlNet encoder tries its best to recognize the input content of the input even if you remove all prompts. Aguidance_scale
between 3.0 and 5.0 is recommended. - return_dict (
bool
, defaults toTrue
) — Whether or not to return a ControlNetOutput instead of a plain tuple.
Returns
ControlNetOutput or tuple
If return_dict
is True
, a ControlNetOutput is returned,
otherwise a tuple is returned where the first element is the sample tensor.
The ControlNetModel forward method.
from_unet
< source >( unet: UNet2DConditionModel controlnet_conditioning_channel_order: str = 'rgb' conditioning_embedding_out_channels: typing.Optional[typing.Tuple[int, ...]] = (16, 32, 96, 256) load_weights_from_unet: bool = True conditioning_channels: int = 3 )
Parameters
- unet (
UNet2DConditionModel
) — The UNet model weights to copy to the ControlNetModel. All configuration options are also copied where applicable.
Instantiate a ControlNetModel from UNet2DConditionModel.
set_attention_slice
< source >( slice_size: typing.Union[str, int, typing.List[int]] )
Parameters
- slice_size (
str
orint
orlist(int)
, optional, defaults to"auto"
) — When"auto"
, input to the attention heads is halved, so attention is computed in two steps. If"max"
, maximum amount of memory is saved by running only one slice at a time. If a number is provided, uses as many slices asattention_head_dim // slice_size
. In this case,attention_head_dim
must be a multiple ofslice_size
.
Enable sliced attention computation.
When this option is enabled, the attention module splits the input tensor in slices to compute attention in several steps. This is useful for saving some memory in exchange for a small decrease in speed.
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]]] )
Parameters
- processor (
dict
ofAttentionProcessor
or onlyAttentionProcessor
) — The instantiated processor class or a dictionary of processor classes that will be set as the processor for allAttention
layers.If
processor
is a dict, the key needs to define the path to the corresponding cross attention processor. This is strongly recommended when setting trainable attention processors.
Sets the attention processor to use to compute attention.
Disables custom attention processors and sets the default attention implementation.
ControlNetOutput
class diffusers.models.controlnets.ControlNetOutput
< source >( down_block_res_samples: typing.Tuple[torch.Tensor] mid_block_res_sample: Tensor )
Parameters
- down_block_res_samples (
tuple[torch.Tensor]
) — A tuple of downsample activations at different resolutions for each downsampling block. Each tensor should be of shape(batch_size, channel * resolution, height //resolution, width // resolution)
. Output can be used to condition the original UNet’s downsampling activations. - mid_down_block_re_sample (
torch.Tensor
) — The activation of the middle block (the lowest sample resolution). Each tensor should be of shape(batch_size, channel * lowest_resolution, height // lowest_resolution, width // lowest_resolution)
. Output can be used to condition the original UNet’s middle block activation.
The output of ControlNetModel.
FlaxControlNetModel
class diffusers.FlaxControlNetModel
< source >( sample_size: int = 32 in_channels: int = 4 down_block_types: typing.Tuple[str, ...] = ('CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D') only_cross_attention: typing.Union[bool, typing.Tuple[bool, ...]] = False block_out_channels: typing.Tuple[int, ...] = (320, 640, 1280, 1280) layers_per_block: int = 2 attention_head_dim: typing.Union[int, typing.Tuple[int, ...]] = 8 num_attention_heads: typing.Union[int, typing.Tuple[int, ...], NoneType] = None cross_attention_dim: int = 1280 dropout: float = 0.0 use_linear_projection: bool = False dtype: dtype = <class 'jax.numpy.float32'> flip_sin_to_cos: bool = True freq_shift: int = 0 controlnet_conditioning_channel_order: str = 'rgb' conditioning_embedding_out_channels: typing.Tuple[int, ...] = (16, 32, 96, 256) parent: typing.Union[flax.linen.module.Module, flax.core.scope.Scope, flax.linen.module._Sentinel, NoneType] = <flax.linen.module._Sentinel object at 0x7f5695c65870> name: typing.Optional[str] = None )
Parameters
- sample_size (
int
, optional) — The size of the input sample. - in_channels (
int
, optional, defaults to 4) — The number of channels in the input sample. - down_block_types (
Tuple[str]
, optional, defaults to("FlaxCrossAttnDownBlock2D", "FlaxCrossAttnDownBlock2D", "FlaxCrossAttnDownBlock2D", "FlaxDownBlock2D")
) — The tuple of downsample blocks to use. - block_out_channels (
Tuple[int]
, optional, defaults to(320, 640, 1280, 1280)
) — The tuple of output channels for each block. - layers_per_block (
int
, optional, defaults to 2) — The number of layers per block. - attention_head_dim (
int
orTuple[int]
, optional, defaults to 8) — The dimension of the attention heads. - num_attention_heads (
int
orTuple[int]
, optional) — The number of attention heads. - cross_attention_dim (
int
, optional, defaults to 768) — The dimension of the cross attention features. - dropout (
float
, optional, defaults to 0) — Dropout probability for down, up and bottleneck blocks. - flip_sin_to_cos (
bool
, optional, defaults toTrue
) — Whether to flip the sin to cos in the time embedding. - freq_shift (
int
, optional, defaults to 0) — The frequency shift to apply to the time embedding. - controlnet_conditioning_channel_order (
str
, optional, defaults torgb
) — The channel order of conditional image. Will convert torgb
if it’sbgr
. - conditioning_embedding_out_channels (
tuple
, optional, defaults to(16, 32, 96, 256)
) — The tuple of output channel for each block in theconditioning_embedding
layer.
A ControlNet model.
This model inherits from FlaxModelMixin. Check the superclass documentation for it’s generic methods implemented for all models (such as downloading or saving).
This model is also a Flax Linen flax.linen.Module
subclass. Use it as a regular Flax Linen module and refer to the Flax documentation for all matters related to its
general usage and behavior.
Inherent JAX features such as the following are supported:
FlaxControlNetOutput
class diffusers.models.controlnets.controlnet_flax.FlaxControlNetOutput
< source >( down_block_res_samples: Array mid_block_res_sample: Array )
The output of FlaxControlNetModel.
Returns a new object replacing the specified fields with new values.