Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / diffusers /pr_13881 /en /api /loaders /lora.md

HuggingFaceDocBuilder

1 minute ago

preview code

download

raw

65.7 kB

LoRA

LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the denoiser, text encoder or both. The denoiser usually corresponds to a UNet (UNet2DConditionModel, for example) or a Transformer (SD3Transformer2DModel, for example). There are several classes for loading LoRA weights:

StableDiffusionLoraLoaderMixin provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
StableDiffusionXLLoraLoaderMixin is a Stable Diffusion (SDXL) version of the StableDiffusionLoraLoaderMixin class for loading and saving LoRA weights. It can only be used with the SDXL model.
SD3LoraLoaderMixin provides similar functions for Stable Diffusion 3.
FluxLoraLoaderMixin provides similar functions for Flux.
CogVideoXLoraLoaderMixin provides similar functions for CogVideoX.
Mochi1LoraLoaderMixin provides similar functions for Mochi.
AuraFlowLoraLoaderMixin provides similar functions for AuraFlow.
LTXVideoLoraLoaderMixin provides similar functions for LTX-Video.
SanaLoraLoaderMixin provides similar functions for Sana.
HeliosLoraLoaderMixin provides similar functions for HunyuanVideo.
HunyuanVideoLoraLoaderMixin provides similar functions for HunyuanVideo.
Lumina2LoraLoaderMixin provides similar functions for Lumina2.
WanLoraLoaderMixin provides similar functions for Wan.
SkyReelsV2LoraLoaderMixin provides similar functions for SkyReels-V2.
CogView4LoraLoaderMixin provides similar functions for CogView4.
AmusedLoraLoaderMixin is for the AmusedPipeline.
AnimaLoraLoaderMixin provides similar functions for Anima.
HiDreamImageLoraLoaderMixin provides similar functions for HiDream Image
QwenImageLoraLoaderMixin provides similar functions for Qwen Image.
ZImageLoraLoaderMixin provides similar functions for Z-Image.
Flux2LoraLoaderMixin provides similar functions for Flux2.
ErnieImageLoraLoaderMixin provides similar functions for Ernie-Image.
LTX2LoraLoaderMixin provides similar functions for Flux2.
LoraBaseMixin provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.

To learn more about how to load LoRA weights, see the LoRA loading guide.

LoraBaseMixin[[diffusers.loaders.lora_base.LoraBaseMixin]]

Utility class for handling LoRAs.

adapter_names (list[str, str]) -- The names of the adapters to delete.

Delete an adapter's LoRA layers from the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_names="cinematic"
)
pipeline.delete_adapters("cinematic")

Disables the active LoRA layers of the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.disable_lora()

Enables the active LoRA layers of the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.enable_lora()

target_rank (int) -- The highest rank among all the adapters that will be loaded.
check_compiled (str, optional, defaults to "error") -- How to handle a model that is already compiled. The check can return the following messages:
- "error" (default): raise an error
- "warn": issue a warning
- "ignore": do nothing

Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are different.

components -- (list[str]): list of LoRA-injectable components to fuse the LoRAs into.
lora_scale (float, defaults to 1.0) -- Controls how much to influence the outputs with the LoRA parameters.
safe_fusing (bool, defaults to False) -- Whether to check fused weights for NaN values before fusing and if values are NaN not fusing them.
adapter_names (list[str], optional) -- Adapter names to be used for fusing. If nothing is passed, all active adapters will be fused.

Fuses the LoRA parameters into the original parameters of the corresponding blocks.

> This is an experimental API.

Example:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
pipeline.fuse_lora(lora_scale=0.7)

Gets the list of the current active adapters.

Example:

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
).to("cuda")
pipeline.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
pipeline.get_active_adapters()

Gets the current list of all available adapters in the pipeline.

adapter_names (list[str] or str) -- The names of the adapters to use.
adapter_weights (list[float, float], optional) -- The adapter(s) weights to use with the UNet. If None, the weights are set to 1.0 for all the adapters.

Set the currently active adapters for use in the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
pipeline.set_adapters(["cinematic", "pixel"], adapter_weights=[0.5, 0.5])

adapter_names (list[str]) -- list of adapters to send device to.
device (torch.device | str | int) -- Device to send the adapters to. Can be either a torch device, a str or an integer.

Moves the LoRAs listed in adapter_names to a target device. Useful for offloading the LoRA to the CPU in case you want to load multiple adapters and free some GPU memory.

After offloading the LoRA adapters to CPU, as long as the rest of the model is still on GPU, the LoRA adapters can no longer be used for inference, as that would cause a device mismatch. Remember to set the device back to GPU before using those LoRA adapters for inference.

>>> pipe.load_lora_weights(path_1, adapter_name="adapter-1")
>>> pipe.load_lora_weights(path_2, adapter_name="adapter-2")
>>> pipe.set_adapters("adapter-1")
>>> image_1 = pipe(**kwargs)
>>> # switch to adapter-2, offload adapter-1
>>> pipeline.set_lora_device(adapter_names=["adapter-1"], device="cpu")
>>> pipeline.set_lora_device(adapter_names=["adapter-2"], device="cuda:0")
>>> pipe.set_adapters("adapter-2")
>>> image_2 = pipe(**kwargs)
>>> # switch back to adapter-1, offload adapter-2
>>> pipeline.set_lora_device(adapter_names=["adapter-2"], device="cpu")
>>> pipeline.set_lora_device(adapter_names=["adapter-1"], device="cuda:0")
>>> pipe.set_adapters("adapter-1")
>>> ...

components (list[str]) -- list of LoRA-injectable components to unfuse LoRA from.
unfuse_unet (bool, defaults to True) -- Whether to unfuse the UNet LoRA parameters.
unfuse_text_encoder (bool, defaults to True) -- Whether to unfuse the text encoder LoRA parameters. If the text encoder wasn't monkey-patched with the LoRA parameters then it won't have any effect.

Reverses the effect of pipe.fuse_lora().

> This is an experimental API.

Unloads the LoRA parameters.

Examples:

>>> # Assuming `pipeline` is already loaded with the LoRA parameters.
>>> pipeline.unload_lora_weights()
>>> ...

Writes the state dict of the LoRA layers (optionally with metadata) to disk.

StableDiffusionLoraLoaderMixin[[diffusers.loaders.StableDiffusionLoraLoaderMixin]]

Load LoRA layers into Stable Diffusion UNet2DConditionModel and CLIPTextModel.

state_dict (dict) -- A standard state dict containing the lora layer parameters. The key should be prefixed with an additional text_encoder to distinguish between unet lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
text_encoder (CLIPTextModel) -- The text encoder model to load the LoRA layers into.
prefix (str) -- Expected prefix of the text_encoder in the state_dict.
lora_scale (float) -- How much to scale the output of the lora linear layer before it is added with the output of the regular lora layer.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading by only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into text_encoder

state_dict (dict) -- A standard state dict containing the lora layer parameters. The keys can either be indexed directly into the unet or prefixed with an additional unet which can be used to distinguish between text encoder lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
unet (UNet2DConditionModel) -- The UNet model to load the LoRA layers into.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into unet.

pretrained_model_name_or_path_or_dict (str or os.PathLike or dict) -- See lora_state_dict().
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading by only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- Defaults to False. Whether to substitute an existing (LoRA) adapter with the newly loaded adapter in-place. This means that, instead of loading an additional adapter, this will take the existing adapter weights and replace them with the weights of the new adapter. This can be faster and more memory efficient. However, the main advantage of hotswapping is that when the model is compiled with torch.compile, loading the new adapter does not require recompilation of the model. When using hotswapping, the passed adapter_name should be the name of an already loaded adapter.

If the new adapter and the old adapter have different ranks and/or LoRA alphas (i.e. scaling), you need to call an additional method before loading the adapter:

pipeline = ...  # load diffusers pipeline
max_rank = ...  # the highest rank among all LoRAs that you want to load
# call *before* compiling and loading the LoRA adapter
pipeline.enable_lora_hotswap(target_rank=max_rank)
pipeline.load_lora_weights(file_name)
# optionally compile the model now

Note that hotswapping adapters of the text encoder is not yet supported. There are some further limitations to this technique, which are documented here: https://huggingface.co/docs/peft/main/en/package_reference/hotswap

kwargs (dict, optional) -- See lora_state_dict(). Load LoRA weights specified in pretrained_model_name_or_path_or_dict into self.unet and self.text_encoder.

All kwargs are forwarded to self.lora_state_dict.

See lora_state_dict() for more details on how the state dict is loaded.

See load_lora_into_unet() for more details on how the state dict is loaded into self.unet.

See load_lora_into_text_encoder() for more details on how the state dict is loaded into self.text_encoder.

pretrained_model_name_or_path_or_dict (str or os.PathLike or dict) -- Can be either:
- A string, the model id (for example google/ddpm-celebahq-256) of a pretrained model hosted on the Hub.
- A path to a directory (for example ./my_model_directory) containing the model weights saved with ModelMixin.save_pretrained().
- A torch state dict.
cache_dir (str | os.PathLike, optional) -- Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used.
force_download (bool, optional, defaults to False) -- Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist.
proxies (dict[str, str], optional) -- A dictionary of proxy servers to use by protocol or endpoint, for example, {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request.
local_files_only (bool, optional, defaults to False) -- Whether to only load local model weights and configuration files or not. If set to True, the model won't be downloaded from the Hub.
token (str or bool, optional) -- The token to use as HTTP bearer authorization for remote files. If True, the token generated from diffusers-cli login (stored in ~/.huggingface) is used.
revision (str, optional, defaults to "main") -- The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier allowed by Git.
subfolder (str, optional, defaults to "") -- The subfolder location of a model file within a larger model repository on the Hub or locally.
weight_name (str, optional, defaults to None) -- Name of the serialized state dict file.
return_lora_metadata (bool, optional, defaults to False) -- When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.

Return state dict for lora weights and the network alphas.

> We support loading A1111 formatted LoRA checkpoints in a limited capacity. > > This function is experimental and might change in the future.

save_directory (str or os.PathLike) -- Directory to save LoRA parameters to. Will be created if it doesn't exist.
unet_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the unet.
text_encoder_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the text_encoder. Must explicitly pass the text encoder LoRA state dict because it comes from 🤗 Transformers.
is_main_process (bool, optional, defaults to True) -- Whether the process calling this is the main process or not. Useful during distributed training and you need to call this function on all processes. In this case, set is_main_process=True only on the main process to avoid race conditions.
save_function (Callable) -- The function to use to save the state dictionary. Useful during distributed training when you need to replace torch.save with another method. Can be configured with the environment variable DIFFUSERS_SAVE_MODE.
safe_serialization (bool, optional, defaults to True) -- Whether to save the model using safetensors or the traditional PyTorch way with pickle.
unet_lora_adapter_metadata -- LoRA adapter metadata associated with the unet to be serialized with the state dict.
text_encoder_lora_adapter_metadata -- LoRA adapter metadata associated with the text encoder to be serialized with the state dict.

Save the LoRA parameters corresponding to the UNet and text encoder.

StableDiffusionXLLoraLoaderMixin[[diffusers.loaders.StableDiffusionXLLoraLoaderMixin]]

Load LoRA layers into Stable Diffusion XL UNet2DConditionModel, CLIPTextModel, and CLIPTextModelWithProjection.

See fuse_lora() for more details.

state_dict (dict) -- A standard state dict containing the lora layer parameters. The key should be prefixed with an additional text_encoder to distinguish between unet lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
text_encoder (CLIPTextModel) -- The text encoder model to load the LoRA layers into.
prefix (str) -- Expected prefix of the text_encoder in the state_dict.
lora_scale (float) -- How much to scale the output of the lora linear layer before it is added with the output of the regular lora layer.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading by only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into text_encoder

state_dict (dict) -- A standard state dict containing the lora layer parameters. The keys can either be indexed directly into the unet or prefixed with an additional unet which can be used to distinguish between text encoder lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
unet (UNet2DConditionModel) -- The UNet model to load the LoRA layers into.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into unet.

See load_lora_weights() for more details.

pretrained_model_name_or_path_or_dict (str or os.PathLike or dict) -- Can be either:
- A string, the model id (for example google/ddpm-celebahq-256) of a pretrained model hosted on the Hub.
- A path to a directory (for example ./my_model_directory) containing the model weights saved with ModelMixin.save_pretrained().
- A torch state dict.
cache_dir (str | os.PathLike, optional) -- Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used.
force_download (bool, optional, defaults to False) -- Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist.
proxies (dict[str, str], optional) -- A dictionary of proxy servers to use by protocol or endpoint, for example, {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request.
local_files_only (bool, optional, defaults to False) -- Whether to only load local model weights and configuration files or not. If set to True, the model won't be downloaded from the Hub.
token (str or bool, optional) -- The token to use as HTTP bearer authorization for remote files. If True, the token generated from diffusers-cli login (stored in ~/.huggingface) is used.
revision (str, optional, defaults to "main") -- The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier allowed by Git.
subfolder (str, optional, defaults to "") -- The subfolder location of a model file within a larger model repository on the Hub or locally.
weight_name (str, optional, defaults to None) -- Name of the serialized state dict file.
return_lora_metadata (bool, optional, defaults to False) -- When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.

Return state dict for lora weights and the network alphas.

> We support loading A1111 formatted LoRA checkpoints in a limited capacity. > > This function is experimental and might change in the future.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

SD3LoraLoaderMixin[[diffusers.loaders.SD3LoraLoaderMixin]]

Load LoRA layers into SD3Transformer2DModel, CLIPTextModel, and CLIPTextModelWithProjection.

Specific to StableDiffusion3Pipeline.

See fuse_lora() for more details.

state_dict (dict) -- A standard state dict containing the lora layer parameters. The key should be prefixed with an additional text_encoder to distinguish between unet lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
text_encoder (CLIPTextModel) -- The text encoder model to load the LoRA layers into.
prefix (str) -- Expected prefix of the text_encoder in the state_dict.
lora_scale (float) -- How much to scale the output of the lora linear layer before it is added with the output of the regular lora layer.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading by only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into text_encoder

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

FluxLoraLoaderMixin[[diffusers.loaders.FluxLoraLoaderMixin]]

Load LoRA layers into FluxTransformer2DModel, CLIPTextModel.

Specific to FluxPipeline.

See lora_state_dict() for more details.

state_dict (dict) -- A standard state dict containing the lora layer parameters. The key should be prefixed with an additional text_encoder to distinguish between unet lora layers.
network_alphas (dict[str, float]) -- The value of the network alpha used for stable learning and preventing underflow. This value has the same meaning as the --network_alpha option in the kohya-ss trainer script. Refer to this link.
text_encoder (CLIPTextModel) -- The text encoder model to load the LoRA layers into.
prefix (str) -- Expected prefix of the text_encoder in the state_dict.
lora_scale (float) -- How much to scale the output of the lora linear layer before it is added with the output of the regular lora layer.
adapter_name (str, optional) -- Adapter name to be used for referencing the loaded adapter model. If not specified, it will use default_{i} where i is the total number of adapters being loaded.
low_cpu_mem_usage (bool, optional) -- Speed up model loading by only loading the pretrained LoRA weights and not initializing the random weights.
hotswap (bool, optional) -- See load_lora_weights().
metadata (dict) -- Optional LoRA adapter metadata. When supplied, the LoraConfig arguments of peft won't be derived from the state dict.

This will load the LoRA layers specified in state_dict into text_encoder

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

save_directory (str or os.PathLike) -- Directory to save LoRA parameters to. Will be created if it doesn't exist.
transformer_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the transformer.
text_encoder_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the text_encoder. Must explicitly pass the text encoder LoRA state dict because it comes from 🤗 Transformers.
is_main_process (bool, optional, defaults to True) -- Whether the process calling this is the main process or not. Useful during distributed training and you need to call this function on all processes. In this case, set is_main_process=True only on the main process to avoid race conditions.
save_function (Callable) -- The function to use to save the state dictionary. Useful during distributed training when you need to replace torch.save with another method. Can be configured with the environment variable DIFFUSERS_SAVE_MODE.
safe_serialization (bool, optional, defaults to True) -- Whether to save the model using safetensors or the traditional PyTorch way with pickle.
transformer_lora_adapter_metadata -- LoRA adapter metadata associated with the transformer to be serialized with the state dict.
text_encoder_lora_adapter_metadata -- LoRA adapter metadata associated with the text encoder to be serialized with the state dict.

Save the LoRA parameters corresponding to the UNet and text encoder.

components (list[str]) -- list of LoRA-injectable components to unfuse LoRA from.

Reverses the effect of pipe.fuse_lora().

> This is an experimental API.

reset_to_overwritten_params (bool, defaults to False) -- Whether to reset the LoRA-loaded modules to their original params. Refer to the Flux documentation to learn more.

Unloads the LoRA parameters.

Examples:

>>> # Assuming `pipeline` is already loaded with the LoRA parameters.
>>> pipeline.unload_lora_weights()
>>> ...

Flux2LoraLoaderMixin[[diffusers.loaders.Flux2LoraLoaderMixin]]

Load LoRA layers into Flux2Transformer2DModel. Specific to Flux2Pipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

ErnieImageLoraLoaderMixin[[diffusers.loaders.ErnieImageLoraLoaderMixin]]

Load LoRA layers into ErnieImageTransformer2DModel. Specific to ErnieImagePipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

LTX2LoraLoaderMixin[[diffusers.loaders.LTX2LoraLoaderMixin]]

Load LoRA layers into LTX2VideoTransformer3DModel. Specific to LTX2Pipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

CogVideoXLoraLoaderMixin[[diffusers.loaders.CogVideoXLoraLoaderMixin]]

Load LoRA layers into CogVideoXTransformer3DModel. Specific to CogVideoXPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

Mochi1LoraLoaderMixin[[diffusers.loaders.Mochi1LoraLoaderMixin]]

Load LoRA layers into MochiTransformer3DModel. Specific to MochiPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

AuraFlowLoraLoaderMixin[[diffusers.loaders.AuraFlowLoraLoaderMixin]]

Load LoRA layers into AuraFlowTransformer2DModel Specific to AuraFlowPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

LTXVideoLoraLoaderMixin[[diffusers.loaders.LTXVideoLoraLoaderMixin]]

Load LoRA layers into LTXVideoTransformer3DModel. Specific to LTXPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

SanaLoraLoaderMixin[[diffusers.loaders.SanaLoraLoaderMixin]]

Load LoRA layers into SanaTransformer2DModel. Specific to SanaPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

HeliosLoraLoaderMixin[[diffusers.loaders.HeliosLoraLoaderMixin]]

Load LoRA layers into HeliosTransformer3DModel. Specific to HeliosPipeline and HeliosPyramidPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

HunyuanVideoLoraLoaderMixin[[diffusers.loaders.HunyuanVideoLoraLoaderMixin]]

Load LoRA layers into HunyuanVideoTransformer3DModel. Specific to HunyuanVideoPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

Lumina2LoraLoaderMixin[[diffusers.loaders.Lumina2LoraLoaderMixin]]

Load LoRA layers into Lumina2Transformer2DModel. Specific to Lumina2Text2ImgPipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

CogView4LoraLoaderMixin[[diffusers.loaders.CogView4LoraLoaderMixin]]

Load LoRA layers into WanTransformer3DModel. Specific to CogView4Pipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

WanLoraLoaderMixin[[diffusers.loaders.WanLoraLoaderMixin]]

Load LoRA layers into WanTransformer3DModel. Specific to WanPipeline and [WanImageToVideoPipeline].

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

SkyReelsV2LoraLoaderMixin[[diffusers.loaders.SkyReelsV2LoraLoaderMixin]]

Load LoRA layers into SkyReelsV2Transformer3DModel.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

AmusedLoraLoaderMixin[[diffusers.loaders.AmusedLoraLoaderMixin]]

See load_lora_into_unet() for more details.

save_directory (str or os.PathLike) -- Directory to save LoRA parameters to. Will be created if it doesn't exist.
unet_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the unet.
text_encoder_lora_layers (dict[str, torch.nn.Module] or dict[str, torch.Tensor]) -- State dict of the LoRA layers corresponding to the text_encoder. Must explicitly pass the text encoder LoRA state dict because it comes from 🤗 Transformers.
is_main_process (bool, optional, defaults to True) -- Whether the process calling this is the main process or not. Useful during distributed training and you need to call this function on all processes. In this case, set is_main_process=True only on the main process to avoid race conditions.
save_function (Callable) -- The function to use to save the state dictionary. Useful during distributed training when you need to replace torch.save with another method. Can be configured with the environment variable DIFFUSERS_SAVE_MODE.
safe_serialization (bool, optional, defaults to True) -- Whether to save the model using safetensors or the traditional PyTorch way with pickle.

Save the LoRA parameters corresponding to the UNet and text encoder.

AnimaLoraLoaderMixin[[diffusers.loaders.AnimaLoraLoaderMixin]]

Load LoRA layers into CosmosTransformer3DModel and AnimaTextConditioner.

See fuse_lora() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See unfuse_lora() for more details.

HiDreamImageLoraLoaderMixin[[diffusers.loaders.HiDreamImageLoraLoaderMixin]]

Load LoRA layers into HiDreamImageTransformer2DModel. Specific to HiDreamImagePipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

QwenImageLoraLoaderMixin[[diffusers.loaders.QwenImageLoraLoaderMixin]]

Load LoRA layers into QwenImageTransformer2DModel. Specific to QwenImagePipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

ZImageLoraLoaderMixin[[diffusers.loaders.ZImageLoraLoaderMixin]]

Load LoRA layers into ZImageTransformer2DModel. Specific to ZImagePipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

CosmosLoraLoaderMixin[[diffusers.loaders.CosmosLoraLoaderMixin]]

Load LoRA layers into CosmosTransformer3DModel, Specific to Cosmos2_5_PredictBasePipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

KandinskyLoraLoaderMixin[[diffusers.loaders.KandinskyLoraLoaderMixin]]

Load LoRA layers into Kandinsky5Transformer3DModel,

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

Ideogram4LoraLoaderMixin[[diffusers.loaders.Ideogram4LoraLoaderMixin]]

Load LoRA layers into Ideogram4Transformer2DModel. Specific to Ideogram4Pipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

Krea2LoraLoaderMixin[[diffusers.loaders.Krea2LoraLoaderMixin]]

Load LoRA layers into Krea2Transformer2DModel. Specific to Krea2Pipeline.

See fuse_lora() for more details.

See load_lora_into_unet() for more details.

See load_lora_weights() for more details.

See lora_state_dict() for more details.

See save_lora_weights() for more information.

See unfuse_lora() for more details.

LoraBaseMixin[[diffusers.loaders.lora_base.LoraBaseMixin]]

Utility class for handling LoRAs.

adapter_names (list[str, str]) -- The names of the adapters to delete.

Delete an adapter's LoRA layers from the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_names="cinematic"
)
pipeline.delete_adapters("cinematic")

Disables the active LoRA layers of the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.disable_lora()

Enables the active LoRA layers of the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.enable_lora()

target_rank (int) -- The highest rank among all the adapters that will be loaded.
check_compiled (str, optional, defaults to "error") -- How to handle a model that is already compiled. The check can return the following messages:
- "error" (default): raise an error
- "warn": issue a warning
- "ignore": do nothing

Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are different.

components -- (list[str]): list of LoRA-injectable components to fuse the LoRAs into.
lora_scale (float, defaults to 1.0) -- Controls how much to influence the outputs with the LoRA parameters.
safe_fusing (bool, defaults to False) -- Whether to check fused weights for NaN values before fusing and if values are NaN not fusing them.
adapter_names (list[str], optional) -- Adapter names to be used for fusing. If nothing is passed, all active adapters will be fused.

Fuses the LoRA parameters into the original parameters of the corresponding blocks.

> This is an experimental API.

Example:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
pipeline.fuse_lora(lora_scale=0.7)

Gets the list of the current active adapters.

Example:

from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
).to("cuda")
pipeline.load_lora_weights("CiroN2022/toy-face", weight_name="toy_face_sdxl.safetensors", adapter_name="toy")
pipeline.get_active_adapters()

Gets the current list of all available adapters in the pipeline.

adapter_names (list[str] or str) -- The names of the adapters to use.
adapter_weights (list[float, float], optional) -- The adapter(s) weights to use with the UNet. If None, the weights are set to 1.0 for all the adapters.

Set the currently active adapters for use in the pipeline.

Example:

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
).to("cuda")
pipeline.load_lora_weights(
    "jbilcke-hf/sdxl-cinematic-1", weight_name="pytorch_lora_weights.safetensors", adapter_name="cinematic"
)
pipeline.load_lora_weights("nerijs/pixel-art-xl", weight_name="pixel-art-xl.safetensors", adapter_name="pixel")
pipeline.set_adapters(["cinematic", "pixel"], adapter_weights=[0.5, 0.5])

adapter_names (list[str]) -- list of adapters to send device to.
device (torch.device | str | int) -- Device to send the adapters to. Can be either a torch device, a str or an integer.

Moves the LoRAs listed in adapter_names to a target device. Useful for offloading the LoRA to the CPU in case you want to load multiple adapters and free some GPU memory.

>>> pipe.load_lora_weights(path_1, adapter_name="adapter-1")
>>> pipe.load_lora_weights(path_2, adapter_name="adapter-2")
>>> pipe.set_adapters("adapter-1")
>>> image_1 = pipe(**kwargs)
>>> # switch to adapter-2, offload adapter-1
>>> pipeline.set_lora_device(adapter_names=["adapter-1"], device="cpu")
>>> pipeline.set_lora_device(adapter_names=["adapter-2"], device="cuda:0")
>>> pipe.set_adapters("adapter-2")
>>> image_2 = pipe(**kwargs)
>>> # switch back to adapter-1, offload adapter-2
>>> pipeline.set_lora_device(adapter_names=["adapter-2"], device="cpu")
>>> pipeline.set_lora_device(adapter_names=["adapter-1"], device="cuda:0")
>>> pipe.set_adapters("adapter-1")
>>> ...

components (list[str]) -- list of LoRA-injectable components to unfuse LoRA from.
unfuse_unet (bool, defaults to True) -- Whether to unfuse the UNet LoRA parameters.
unfuse_text_encoder (bool, defaults to True) -- Whether to unfuse the text encoder LoRA parameters. If the text encoder wasn't monkey-patched with the LoRA parameters then it won't have any effect.

Reverses the effect of pipe.fuse_lora().

> This is an experimental API.

Unloads the LoRA parameters.

Examples:

>>> # Assuming `pipeline` is already loaded with the LoRA parameters.
>>> pipeline.unload_lora_weights()
>>> ...

Writes the state dict of the LoRA layers (optionally with metadata) to disk.

Xet Storage Details

Size:: 65.7 kB
Xet hash:: ed24aec8903f6e6f3748e72e30dbc3ed4738f61fc34044035a2d888dd85e7c82

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.