Single files
Diffusers supports loading pretrained pipeline (or model) weights stored in a single file, such as a ckpt
or safetensors
file. These single file types are typically produced from community trained models. There are three classes for loading single file weights:
FromSingleFileMixin
supports loading pretrained pipeline weights stored in a single file, which can either be ackpt
orsafetensors
file.FromOriginalVAEMixin
supports loading a pretrained AutoencoderKL from pretrained ControlNet weights stored in a single file, which can either be ackpt
orsafetensors
file.FromOriginalControlnetMixin
supports loading pretrained ControlNet weights stored in a single file, which can either be ackpt
orsafetensors
file.
To learn more about how to load single file weights, see the Load different Stable Diffusion formats loading guide.
FromSingleFileMixin
Load model weights saved in the .ckpt
format into a DiffusionPipeline.
from_single_file
< source >( pretrained_model_link_or_path **kwargs )
Parameters
- pretrained_model_link_or_path (
str
oros.PathLike
, optional) — Can be either:- A link to the
.ckpt
file (for example"https://huggingface.co/<repo_id>/blob/main/<path_to_file>.ckpt"
) on the Hub. - A path to a file containing all pipeline weights.
- A link to the
- torch_dtype (
str
ortorch.dtype
, optional) — Override the defaulttorch.dtype
and load the model with another dtype. If"auto"
is passed, the dtype is automatically derived from the model’s weights. - force_download (
bool
, optional, defaults toFalse
) — Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. - cache_dir (
Union[str, os.PathLike]
, optional) — Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. - resume_download (
bool
, optional, defaults toFalse
) — Whether or not to resume downloading the model weights and configuration files. If set toFalse
, any incompletely downloaded files are deleted. - 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 toFalse
) — Whether to only load local model weights and configuration files or not. If set toTrue
, the model won’t be downloaded from the Hub. - use_auth_token (
str
or bool, optional) — The token to use as HTTP bearer authorization for remote files. IfTrue
, the token generated fromdiffusers-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. - use_safetensors (
bool
, optional, defaults toNone
) — If set toNone
, the safetensors weights are downloaded if they’re available and if the safetensors library is installed. If set toTrue
, the model is forcibly loaded from safetensors weights. If set toFalse
, safetensors weights are not loaded. - extract_ema (
bool
, optional, defaults toFalse
) — Whether to extract the EMA weights or not. PassTrue
to extract the EMA weights which usually yield higher quality images for inference. Non-EMA weights are usually better for continuing finetuning. - upcast_attention (
bool
, optional, defaults toNone
) — Whether the attention computation should always be upcasted. - image_size (
int
, optional, defaults to 512) — The image size the model was trained on. Use 512 for all Stable Diffusion v1 models and the Stable Diffusion v2 base model. Use 768 for Stable Diffusion v2. - prediction_type (
str
, optional) — The prediction type the model was trained on. Use'epsilon'
for all Stable Diffusion v1 models and the Stable Diffusion v2 base model. Use'v_prediction'
for Stable Diffusion v2. - num_in_channels (
int
, optional, defaults toNone
) — The number of input channels. IfNone
, it is automatically inferred. - scheduler_type (
str
, optional, defaults to"pndm"
) — Type of scheduler to use. Should be one of["pndm", "lms", "heun", "euler", "euler-ancestral", "dpm", "ddim"]
. - load_safety_checker (
bool
, optional, defaults toTrue
) — Whether to load the safety checker or not. - text_encoder (CLIPTextModel, optional, defaults to
None
) — An instance ofCLIPTextModel
to use, specifically the clip-vit-large-patch14 variant. If this parameter isNone
, the function loads a new instance ofCLIPTextModel
by itself if needed. - vae (
AutoencoderKL
, optional, defaults toNone
) — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations. If this parameter isNone
, the function will load a new instance of [CLIP] by itself, if needed. - tokenizer (CLIPTokenizer, optional, defaults to
None
) — An instance ofCLIPTokenizer
to use. If this parameter isNone
, the function loads a new instance ofCLIPTokenizer
by itself if needed. - original_config_file (
str
) — Path to.yaml
config file corresponding to the original architecture. IfNone
, will be automatically inferred by looking for a key that only exists in SD2.0 models. - kwargs (remaining dictionary of keyword arguments, optional) —
Can be used to overwrite load and saveable variables (for example the pipeline components of the
specific pipeline class). The overwritten components are directly passed to the pipelines
__init__
method. See example below for more information.
Instantiate a DiffusionPipeline from pretrained pipeline weights saved in the .ckpt
or .safetensors
format. The pipeline is set in evaluation mode (model.eval()
) by default.
Examples:
>>> from diffusers import StableDiffusionPipeline
>>> # Download pipeline from huggingface.co and cache.
>>> pipeline = StableDiffusionPipeline.from_single_file(
... "https://huggingface.co/WarriorMama777/OrangeMixs/blob/main/Models/AbyssOrangeMix/AbyssOrangeMix.safetensors"
... )
>>> # Download pipeline from local file
>>> # file is downloaded under ./v1-5-pruned-emaonly.ckpt
>>> pipeline = StableDiffusionPipeline.from_single_file("./v1-5-pruned-emaonly")
>>> # Enable float16 and move to GPU
>>> pipeline = StableDiffusionPipeline.from_single_file(
... "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt",
... torch_dtype=torch.float16,
... )
>>> pipeline.to("cuda")
FromOriginalVAEMixin
Load pretrained ControlNet weights saved in the .ckpt
or .safetensors
format into an AutoencoderKL.
from_single_file
< source >( pretrained_model_link_or_path **kwargs )
Parameters
- pretrained_model_link_or_path (
str
oros.PathLike
, optional) — Can be either:- A link to the
.ckpt
file (for example"https://huggingface.co/<repo_id>/blob/main/<path_to_file>.ckpt"
) on the Hub. - A path to a file containing all pipeline weights.
- A link to the
- torch_dtype (
str
ortorch.dtype
, optional) — Override the defaulttorch.dtype
and load the model with another dtype. If"auto"
is passed, the dtype is automatically derived from the model’s weights. - force_download (
bool
, optional, defaults toFalse
) — Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. - cache_dir (
Union[str, os.PathLike]
, optional) — Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. - resume_download (
bool
, optional, defaults toFalse
) — Whether or not to resume downloading the model weights and configuration files. If set toFalse
, any incompletely downloaded files are deleted. - 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 toFalse
) — 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. - use_auth_token (
str
or bool, optional) — The token to use as HTTP bearer authorization for remote files. IfTrue
, the token generated fromdiffusers-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. - image_size (
int
, optional, defaults to 512) — The image size the model was trained on. Use 512 for all Stable Diffusion v1 models and the Stable Diffusion v2 base model. Use 768 for Stable Diffusion v2. - use_safetensors (
bool
, optional, defaults toNone
) — If set toNone
, the safetensors weights are downloaded if they’re available and if the safetensors library is installed. If set toTrue
, the model is forcibly loaded from safetensors weights. If set toFalse
, safetensors weights are not loaded. - upcast_attention (
bool
, optional, defaults toNone
) — Whether the attention computation should always be upcasted. - scaling_factor (
float
, optional, defaults to 0.18215) — The component-wise standard deviation of the trained latent space computed using the first batch of the training set. This is used to scale the latent space to have unit variance when training the diffusion model. The latents are scaled with the formulaz = z * scaling_factor
before being passed to the diffusion model. When decoding, the latents are scaled back to the original scale with the formula:z = 1 / scaling_factor * z
. For more details, refer to sections 4.3.2 and D.1 of the High-Resolution Image Synthesis with Latent Diffusion Models paper. - kwargs (remaining dictionary of keyword arguments, optional) —
Can be used to overwrite load and saveable variables (for example the pipeline components of the
specific pipeline class). The overwritten components are directly passed to the pipelines
__init__
method. See example below for more information.
Instantiate a AutoencoderKL from pretrained ControlNet weights saved in the original .ckpt
or
.safetensors
format. The pipeline is set in evaluation mode (model.eval()
) by default.
Make sure to pass both image_size
and scaling_factor
to from_single_file()
if you’re loading
a VAE from SDXL or a Stable Diffusion v2 model or higher.
FromOriginalControlnetMixin
Load pretrained ControlNet weights saved in the .ckpt
or .safetensors
format into a ControlNetModel.
from_single_file
< source >( pretrained_model_link_or_path **kwargs )
Parameters
- pretrained_model_link_or_path (
str
oros.PathLike
, optional) — Can be either:- A link to the
.ckpt
file (for example"https://huggingface.co/<repo_id>/blob/main/<path_to_file>.ckpt"
) on the Hub. - A path to a file containing all pipeline weights.
- A link to the
- torch_dtype (
str
ortorch.dtype
, optional) — Override the defaulttorch.dtype
and load the model with another dtype. If"auto"
is passed, the dtype is automatically derived from the model’s weights. - force_download (
bool
, optional, defaults toFalse
) — Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. - cache_dir (
Union[str, os.PathLike]
, optional) — Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. - resume_download (
bool
, optional, defaults toFalse
) — Whether or not to resume downloading the model weights and configuration files. If set toFalse
, any incompletely downloaded files are deleted. - 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 toFalse
) — 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. - use_auth_token (
str
or bool, optional) — The token to use as HTTP bearer authorization for remote files. IfTrue
, the token generated fromdiffusers-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. - use_safetensors (
bool
, optional, defaults toNone
) — If set toNone
, the safetensors weights are downloaded if they’re available and if the safetensors library is installed. If set toTrue
, the model is forcibly loaded from safetensors weights. If set toFalse
, safetensors weights are not loaded. - image_size (
int
, optional, defaults to 512) — The image size the model was trained on. Use 512 for all Stable Diffusion v1 models and the Stable Diffusion v2 base model. Use 768 for Stable Diffusion v2. - upcast_attention (
bool
, optional, defaults toNone
) — Whether the attention computation should always be upcasted. - kwargs (remaining dictionary of keyword arguments, optional) —
Can be used to overwrite load and saveable variables (for example the pipeline components of the
specific pipeline class). The overwritten components are directly passed to the pipelines
__init__
method. See example below for more information.
Instantiate a ControlNetModel from pretrained ControlNet weights saved in the original .ckpt
or
.safetensors
format. The pipeline is set in evaluation mode (model.eval()
) by default.
Examples:
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
model = ControlNetModel.from_single_file(url)
url = "https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned.safetensors" # can also be a local path
pipe = StableDiffusionControlNetPipeline.from_single_file(url, controlnet=controlnet)