mmagic.models.editors.stable_diffusion
¶
Package Contents¶
Classes¶
Class for Stable Diffusion. Refers to https://github.com/Stability- |
|
Class for Stable Diffusion. Refers to https://github.com/Stability- |
|
Variational Autoencoder (VAE) model with KL loss |
- class mmagic.models.editors.stable_diffusion.StableDiffusion(vae: ModelType, text_encoder: ModelType, tokenizer: str, unet: ModelType, scheduler: ModelType, test_scheduler: Optional[ModelType] = None, dtype: Optional[str] = None, enable_xformers: bool = True, noise_offset_weight: float = 0, tomesd_cfg: Optional[dict] = None, data_preprocessor: Optional[ModelType] = dict(type='DataPreprocessor'), init_cfg: Optional[dict] = None)[source]¶
Bases:
mmengine.model.BaseModel
Class for Stable Diffusion. Refers to https://github.com/Stability- AI/stablediffusion and https://github.com/huggingface/diffusers/blob/main/s rc/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_an d_excite.py # noqa.
- Parameters
unet (Union[dict, nn.Module]) – The config or module for Unet model.
text_encoder (Union[dict, nn.Module]) – The config or module for text encoder.
vae (Union[dict, nn.Module]) – The config or module for VAE model.
tokenizer (str) – The name for CLIP tokenizer.
schedule (Union[dict, nn.Module]) – The config or module for diffusion scheduler.
test_scheduler (Union[dict, nn.Module], optional) – The config or module for diffusion scheduler in test stage (self.infer). If not passed, will use the same scheduler as schedule. Defaults to None.
dtype (str, optional) – The dtype for the model This argument will not work when dtype is defined for submodels. Defaults to None.
enable_xformers (bool, optional) – Whether to use xformers. Defaults to True.
noise_offset_weight (bool, optional) – The weight of noise offset introduced in https://www.crosslabs.org/blog/diffusion-with-offset-noise Defaults to 0.
data_preprocessor (dict, optional) – The pre-process config of
BaseDataPreprocessor
.init_cfg (dict, optional) – The weight initialized config for
BaseModule
.
- property device¶
- set_xformers(module: Optional[torch.nn.Module] = None) torch.nn.Module [source]¶
Set xformers for the model.
- Returns
The model with xformers.
- Return type
nn.Module
- set_tomesd() torch.nn.Module [source]¶
Set ToMe for the stable diffusion model.
- Returns
The model with ToMe.
- Return type
nn.Module
- train(mode: bool = True)[source]¶
Set train/eval mode.
- Parameters
mode (bool, optional) – Whether set train mode. Defaults to True.
- infer(prompt: Union[str, List[str]], height: Optional[int] = None, width: Optional[int] = None, num_inference_steps: int = 50, guidance_scale: float = 7.5, negative_prompt: Optional[Union[str, List[str]]] = None, num_images_per_prompt: Optional[int] = 1, eta: float = 0.0, generator: Optional[torch.Generator] = None, latents: Optional[torch.FloatTensor] = None, show_progress=True, seed=1, return_type='image')[source]¶
Function invoked when calling the pipeline for generation.
- Parameters
prompt (str or List[str]) – The prompt or prompts to guide the image generation.
(int (height) – defaults to self.unet_sample_size * self.vae_scale_factor): The height in pixels of the generated image.
optional – defaults to self.unet_sample_size * self.vae_scale_factor): The height in pixels of the generated image.
- :paramdefaults to self.unet_sample_size * self.vae_scale_factor):
The height in pixels of the generated image.
- Parameters
(int (width) – defaults to self.unet_sample_size * self.vae_scale_factor): The width in pixels of the generated image.
optional – defaults to self.unet_sample_size * self.vae_scale_factor): The width in pixels of the generated image.
- :paramdefaults to self.unet_sample_size * self.vae_scale_factor):
The width in pixels of the generated image.
- Parameters
num_inference_steps (int, optional, defaults to 50) – The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
guidance_scale (float, optional, defaults to 7.5) – Guidance scale as defined in [Classifier-Free Diffusion Guidance] (https://arxiv.org/abs/2207.12598).
negative_prompt (str or List[str], optional) – The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
num_images_per_prompt (int, optional, defaults to 1) – The number of images to generate per prompt.
eta (float, optional, defaults to 0.0) – Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to [schedulers.DDIMScheduler], will be ignored for others.
generator (torch.Generator, optional) – A [torch generator] to make generation deterministic.
latents (torch.FloatTensor, optional) – Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
return_type (str) – The return type of the inference results. Supported types are ‘image’, ‘numpy’, ‘tensor’. If ‘image’ is passed, a list of PIL images will be returned. If ‘numpy’ is passed, a numpy array with shape [N, C, H, W] will be returned, and the value range will be same as decoder’s output range. If ‘tensor’ is passed, the decoder’s output will be returned. Defaults to ‘image’.
- Returns
A dict containing the generated images.
- Return type
dict
- output_to_pil(image) List[PIL.Image.Image] [source]¶
Convert output tensor to PIL image. Output tensor will be de-normed to [0, 255] by DataPreprocessor.destruct. Due to no data_samples is passed, color order conversion will not be performed.
- Parameters
image (torch.Tensor) – The output tensor of the decoder.
- Returns
The list of processed PIL images.
- Return type
List[Image.Image]
- _encode_prompt(prompt, device, num_images_per_prompt, do_classifier_free_guidance, negative_prompt)[source]¶
Encodes the prompt into text encoder hidden states.
- Parameters
prompt (str or list(int)) – prompt to be encoded.
device – (torch.device): torch device.
num_images_per_prompt (int) – number of images that should be generated per prompt.
do_classifier_free_guidance (bool) – whether to use classifier free guidance or not.
negative_prompt (str or List[str]) – The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
- Returns
- text embeddings generated by
clip text encoder.
- Return type
text_embeddings (torch.Tensor)
- decode_latents(latents)[source]¶
use vae to decode latents.
- Parameters
latents (torch.Tensor) – latents to decode.
- Returns
image result.
- Return type
image (torch.Tensor)
- prepare_extra_step_kwargs(generator, eta)[source]¶
prepare extra kwargs for the scheduler step.
- Parameters
generator (torch.Generator) – generator for random functions.
eta (float) – eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers. eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502 and should be between [0, 1]
- Returns
dict contains ‘generator’ and ‘eta’
- Return type
extra_step_kwargs (dict)
- prepare_test_scheduler_extra_step_kwargs(generator, eta)[source]¶
prepare extra kwargs for the scheduler step.
- Parameters
generator (torch.Generator) – generator for random functions.
eta (float) – eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers. eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502 and should be between [0, 1]
- Returns
dict contains ‘generator’ and ‘eta’
- Return type
extra_step_kwargs (dict)
- prepare_latents(batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None)[source]¶
prepare latents for diffusion to run in latent space.
- Parameters
batch_size (int) – batch size.
num_channels_latents (int) – latent channel nums.
height (int) – image height.
width (int) – image width.
dtype (torch.dtype) – float type.
device (torch.device) – torch device.
generator (torch.Generator) – generator for random functions, defaults to None.
latents (torch.Tensor) – Pre-generated noisy latents, defaults to None.
- Returns
prepared latents.
- Return type
latents (torch.Tensor)
- val_step(data: dict) mmagic.utils.typing.SampleList [source]¶
Gets the predictions of given data.
Calls
self.data_preprocessor(data, False)
andself(inputs, data_sample, mode='predict')
in order. Return the predictions which will be passed to evaluator.- Parameters
data (dict or tuple or list) – Data sampled from dataset.
- Returns
The predictions of given data.
- Return type
list
- test_step(data: dict) mmagic.utils.typing.SampleList [source]¶
BaseModel
implementstest_step
the same asval_step
.- Parameters
data (dict or tuple or list) – Data sampled from dataset.
- Returns
The predictions of given data.
- Return type
list
- train_step(data, optim_wrapper_dict)[source]¶
Implements the default model training process including preprocessing, model forward propagation, loss calculation, optimization, and back-propagation.
During non-distributed training. If subclasses do not override the
train_step()
,EpochBasedTrainLoop
orIterBasedTrainLoop
will call this method to update model parameters. The default parameter update process is as follows:Calls
self.data_processor(data, training=False)
to collect batch_inputs and corresponding data_samples(labels).Calls
self(batch_inputs, data_samples, mode='loss')
to get raw lossCalls
self.parse_losses
to getparsed_losses
tensor used to backward and dict of loss tensor used to log messages.Calls
optim_wrapper.update_params(loss)
to update model.
- Parameters
data (dict or tuple or list) – Data sampled from dataset.
optim_wrapper (OptimWrapper) – OptimWrapper instance used to update model parameters.
- Returns
A
dict
of tensor for logging.- Return type
Dict[str, torch.Tensor]
- class mmagic.models.editors.stable_diffusion.StableDiffusionInpaint(*args, **kwargs)[source]¶
Bases:
mmagic.models.editors.stable_diffusion.stable_diffusion.StableDiffusion
Class for Stable Diffusion. Refers to https://github.com/Stability- AI/stablediffusion and https://github.com/huggingface/diffusers/blob/main/s rc/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_an d_excite.py # noqa.
- Parameters
unet (Union[dict, nn.Module]) – The config or module for Unet model.
text_encoder (Union[dict, nn.Module]) – The config or module for text encoder.
vae (Union[dict, nn.Module]) – The config or module for VAE model.
tokenizer (str) – The name for CLIP tokenizer.
schedule (Union[dict, nn.Module]) – The config or module for diffusion scheduler.
test_scheduler (Union[dict, nn.Module], optional) – The config or module for diffusion scheduler in test stage (self.infer). If not passed, will use the same scheduler as schedule. Defaults to None.
dtype (str, optional) – The dtype for the model This argument will not work when dtype is defined for submodels. Defaults to None.
enable_xformers (bool, optional) – Whether to use xformers. Defaults to True.
noise_offset_weight (bool, optional) – The weight of noise offset introduced in https://www.crosslabs.org/blog/diffusion-with-offset-noise Defaults to 0.
data_preprocessor (dict, optional) – The pre-process config of
BaseDataPreprocessor
.init_cfg (dict, optional) – The weight initialized config for
BaseModule
.
- infer(prompt: Union[str, List[str]], image: Union[torch.FloatTensor, PIL.Image.Image] = None, mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None, height: Optional[int] = None, width: Optional[int] = None, num_inference_steps: int = 50, guidance_scale: float = 7.5, negative_prompt: Optional[Union[str, List[str]]] = None, num_images_per_prompt: Optional[int] = 1, eta: float = 0.0, generator: Optional[torch.Generator] = None, latents: Optional[torch.FloatTensor] = None, show_progress=True, seed=1, return_type='image')[source]¶
Function invoked when calling the pipeline for generation.
- Parameters
prompt (str or List[str]) – The prompt or prompts to guide the image generation.
image (Union[torch.FloatTensor, Image.Image]) – The image to inpaint.
mask_image (Union[torch.FloatTensor, Image.Image]) – The mask to apply to the image, i.e. regions to inpaint.
(int (height) – defaults to self.unet_sample_size * self.vae_scale_factor): The height in pixels of the generated image.
optional – defaults to self.unet_sample_size * self.vae_scale_factor): The height in pixels of the generated image.
- :paramdefaults to self.unet_sample_size * self.vae_scale_factor):
The height in pixels of the generated image.
- Parameters
(int (width) – defaults to self.unet_sample_size * self.vae_scale_factor): The width in pixels of the generated image.
optional – defaults to self.unet_sample_size * self.vae_scale_factor): The width in pixels of the generated image.
- :paramdefaults to self.unet_sample_size * self.vae_scale_factor):
The width in pixels of the generated image.
- Parameters
num_inference_steps (int, optional, defaults to 50) – The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
guidance_scale (float, optional, defaults to 7.5) – Guidance scale as defined in [Classifier-Free Diffusion Guidance] (https://arxiv.org/abs/2207.12598).
negative_prompt (str or List[str], optional) – The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
num_images_per_prompt (int, optional, defaults to 1) – The number of images to generate per prompt.
eta (float, optional, defaults to 0.0) – Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to [schedulers.DDIMScheduler], will be ignored for others.
generator (torch.Generator, optional) – A [torch generator] to make generation deterministic.
latents (torch.FloatTensor, optional) – Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
return_type (str) – The return type of the inference results. Supported types are ‘image’, ‘numpy’, ‘tensor’. If ‘image’ is passed, a list of PIL images will be returned. If ‘numpy’ is passed, a numpy array with shape [N, C, H, W] will be returned, and the value range will be same as decoder’s output range. If ‘tensor’ is passed, the decoder’s output will be returned. Defaults to ‘image’.
- Returns
A dict containing the generated images.
- Return type
dict
- prepare_mask_latents(mask, masked_image, batch_size, num_channels_latents, height, width, dtype, device, generator, do_classifier_free_guidance)[source]¶
prepare latents for diffusion to run in latent space.
- Parameters
mask (torch.Tensor) – The mask to apply to the image, i.e. regions to inpaint.
image (torch.Tensor) – The image to be masked.
batch_size (int) – batch size.
num_channels_latents (int) – latent channel nums.
height (int) – image height.
width (int) – image width.
dtype (torch.dtype) – float type.
device (torch.device) – torch device.
generator (torch.Generator) – generator for random functions, defaults to None.
latents (torch.Tensor) – Pre-generated noisy latents, defaults to None.
do_classifier_free_guidance (bool) – Whether to apply classifier-free guidance.
- Returns
prepared latents.
- Return type
latents (torch.Tensor)
- abstract val_step(data: dict) mmagic.utils.typing.SampleList [source]¶
Performs a validation step on the provided data.
This method is decorated with torch.no_grad() which indicates no gradients will be computed during the operations. This ensures efficient memory usage during testing.
- Parameters
data (dict) – Dictionary containing input data for testing.
- Returns
List of samples processed during the testing step.
- Return type
SampleList
- Raises
NotImplementedError – This method has not been implemented.
- abstract test_step(data: dict) mmagic.utils.typing.SampleList [source]¶
Performs a testing step on the provided data.
This method is decorated with torch.no_grad() which indicates no gradients will be computed during the operations. This ensures efficient memory usage during testing.
- Parameters
data (dict) – Dictionary containing input data for testing.
- Returns
List of samples processed during the testing step.
- Return type
SampleList
- Raises
NotImplementedError – This method has not been implemented.
- abstract train_step(data, optim_wrapper_dict)[source]¶
Performs a training step on the provided data.
- Parameters
data – Input data for training.
optim_wrapper_dict – Dictionary containing optimizer wrappers which may contain optimizers, schedulers, etc. required for the training step.
- Raises
NotImplementedError – This method has not been implemented.
- class mmagic.models.editors.stable_diffusion.AutoencoderKL(in_channels: int = 3, out_channels: int = 3, down_block_types: Tuple[str] = ('DownEncoderBlock2D',), up_block_types: Tuple[str] = ('UpDecoderBlock2D',), block_out_channels: Tuple[int] = (64,), layers_per_block: int = 1, act_fn: str = 'silu', latent_channels: int = 4, norm_num_groups: int = 32, sample_size: int = 32)[source]¶
Bases:
torch.nn.Module
Variational Autoencoder (VAE) model with KL loss from the paper Auto-Encoding Variational Bayes by Diederik P. Kingma and Max Welling.
- Parameters
in_channels (int, optional, defaults to 3) – Number of channels in the input image.
out_channels (int, optional, defaults to 3) – Number of channels in the output.
(Tuple[str] (up_block_types) – obj:(“DownEncoderBlock2D”,)): Tuple of downsample block types.
optional – obj:(“DownEncoderBlock2D”,)): Tuple of downsample block types.
to (defaults) – obj:(“DownEncoderBlock2D”,)): Tuple of downsample block types.
(Tuple[str] – obj:(“UpDecoderBlock2D”,)): Tuple of upsample block types.
optional – obj:(“UpDecoderBlock2D”,)): Tuple of upsample block types.
to – obj:(“UpDecoderBlock2D”,)): Tuple of upsample block types.
(Tuple[int] (block_out_channels) – obj:(64,)): Tuple of block output channels.
optional – obj:(64,)): Tuple of block output channels.
to – obj:(64,)): Tuple of block output channels.
act_fn (str, optional, defaults to “silu”) – The activation function to use.
latent_channels (int, optional, defaults to 4) – Number of channels in the latent space.
sample_size (int, optional, defaults to 32) – sample size is now not supported.
- property dtype¶
The data type of the parameters of VAE.
- decode(z: torch.FloatTensor, return_dict: bool = True) Union[addict.Dict, torch.FloatTensor] [source]¶
decode z.
- forward(sample: torch.FloatTensor, sample_posterior: bool = False, return_dict: bool = True, generator: Optional[torch.Generator] = None) Union[addict.Dict, torch.FloatTensor] [source]¶
- Parameters
sample (torch.FloatTensor) – Input sample.
sample_posterior (bool) – Whether to sample from the posterior. defaults to False.
return_dict (bool, optional, defaults to True) – Whether or not to return a [Dict] instead of a plain tuple.
- Returns
decode results.
- Return type
Dict(sample=dec)