Diffusers documentation
SD3ControlNetModel
SD3ControlNetModel
SD3ControlNetModel is an implementation of ControlNet for Stable Diffusion 3.
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 SD3ControlNetModel should be loaded with from_pretrained().
from diffusers import StableDiffusion3ControlNetPipeline
from diffusers.models import SD3ControlNetModel, SD3MultiControlNetModel
controlnet = SD3ControlNetModel.from_pretrained("InstantX/SD3-Controlnet-Canny")
pipe = StableDiffusion3ControlNetPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", controlnet=controlnet)SD3ControlNetModel
class diffusers.SD3ControlNetModel
< source >( sample_size: int = 128 patch_size: int = 2 in_channels: int = 16 num_layers: int = 18 attention_head_dim: int = 64 num_attention_heads: int = 18 joint_attention_dim: int = 4096 caption_projection_dim: int = 1152 pooled_projection_dim: int = 2048 out_channels: int = 16 pos_embed_max_size: int = 96 extra_conditioning_channels: int = 0 dual_attention_layers: typing.Tuple[int, ...] = () qk_norm: typing.Optional[str] = None pos_embed_type: typing.Optional[str] = 'sincos' use_pos_embed: bool = True force_zeros_for_pooled_projection: bool = True )
Parameters
- sample_size (
int, defaults to128) — The width/height of the latents. This is fixed during training since it is used to learn a number of position embeddings. - patch_size (
int, defaults to2) — Patch size to turn the input data into small patches. - in_channels (
int, defaults to16) — The number of latent channels in the input. - num_layers (
int, defaults to18) — The number of layers of transformer blocks to use. - attention_head_dim (
int, defaults to64) — The number of channels in each head. - num_attention_heads (
int, defaults to18) — The number of heads to use for multi-head attention. - joint_attention_dim (
int, defaults to4096) — The embedding dimension to use for joint text-image attention. - caption_projection_dim (
int, defaults to1152) — The embedding dimension of caption embeddings. - pooled_projection_dim (
int, defaults to2048) — The embedding dimension of pooled text projections. - out_channels (
int, defaults to16) — The number of latent channels in the output. - pos_embed_max_size (
int, defaults to96) — The maximum latent height/width of positional embeddings. - extra_conditioning_channels (
int, defaults to0) — The number of extra channels to use for conditioning for patch embedding. - dual_attention_layers (
Tuple[int, ...], defaults to()) — The number of dual-stream transformer blocks to use. - qk_norm (
str, optional, defaults toNone) — The normalization to use for query and key in the attention layer. IfNone, no normalization is used. - pos_embed_type (
str, defaults to"sincos") — The type of positional embedding to use. Choose between"sincos"andNone. - use_pos_embed (
bool, defaults toTrue) — Whether to use positional embeddings. - force_zeros_for_pooled_projection (
bool, defaults toTrue) — Whether to force zeros for pooled projection embeddings. This is handled in the pipelines by reading the config value of the ControlNet model.
ControlNet model for Stable Diffusion 3.
enable_forward_chunking
< source >( chunk_size: typing.Optional[int] = None dim: int = 0 )
Parameters
- chunk_size (
int, optional) — The chunk size of the feed-forward layers. If not specified, will run feed-forward layer individually over each tensor of dim=dim. - dim (
int, optional, defaults to0) — The dimension over which the feed-forward computation should be chunked. Choose between dim=0 (batch) or dim=1 (sequence length).
Sets the attention processor to use feed forward chunking.
forward
< source >( hidden_states: Tensor controlnet_cond: Tensor conditioning_scale: float = 1.0 encoder_hidden_states: Tensor = None pooled_projections: Tensor = None timestep: LongTensor = None joint_attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None return_dict: bool = True )
Parameters
- hidden_states (
torch.Tensorof shape(batch size, channel, height, width)) — Inputhidden_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. - encoder_hidden_states (
torch.Tensorof shape(batch size, sequence_len, embed_dims)) — Conditional embeddings (embeddings computed from the input conditions such as prompts) to use. - pooled_projections (
torch.Tensorof shape(batch_size, projection_dim)) — Embeddings projected from the embeddings of input conditions. - timestep (
torch.LongTensor) — Used to indicate denoising step. - joint_attention_kwargs (
dict, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessoras defined underself.processorin diffusers.models.attention_processor. - return_dict (
bool, optional, defaults toTrue) — Whether or not to return a~models.transformer_2d.Transformer2DModelOutputinstead of a plain tuple.
The SD3Transformer2DModel forward method.
Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value) are fused. For cross-attention modules, key and value projection matrices are fused.
This API is 🧪 experimental.
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 (
dictofAttentionProcessoror onlyAttentionProcessor) — The instantiated processor class or a dictionary of processor classes that will be set as the processor for allAttentionlayers.If
processoris 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 the fused QKV projection if enabled.
This API is 🧪 experimental.
SD3ControlNetOutput
class diffusers.models.controlnets.SD3ControlNetOutput
< source >( controlnet_block_samples: typing.Tuple[torch.Tensor] )