DiT
Scalable Diffusion Models with Transformers (DiT) is by William Peebles and Saining Xie.
The abstract from the paper is:
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops — through increased transformer depth/width or increased number of input tokens — consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512x512 and 256x256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
The original codebase can be found at facebookresearch/dit.
Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.
DiTPipeline
class diffusers.DiTPipeline
< source >( transformer: DiTTransformer2DModel vae: AutoencoderKL scheduler: KarrasDiffusionSchedulers id2label: Optional = None )
Parameters
- transformer (DiTTransformer2DModel) —
A class conditioned
DiTTransformer2DModel
to denoise the encoded image latents. - vae (AutoencoderKL) — Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
- scheduler (DDIMScheduler) —
A scheduler to be used in combination with
transformer
to denoise the encoded image latents.
Pipeline for image generation based on a Transformer backbone instead of a UNet.
This model inherits from DiffusionPipeline. Check the superclass documentation for the generic methods implemented for all pipelines (downloading, saving, running on a particular device, etc.).
__call__
< source >( class_labels: List guidance_scale: float = 4.0 generator: Union = None num_inference_steps: int = 50 output_type: Optional = 'pil' return_dict: bool = True ) → ImagePipelineOutput or tuple
Parameters
- class_labels (List[int]) — List of ImageNet class labels for the images to be generated.
- guidance_scale (
float
, optional, defaults to 4.0) — A higher guidance scale value encourages the model to generate images closely linked to the textprompt
at the expense of lower image quality. Guidance scale is enabled whenguidance_scale > 1
. - generator (
torch.Generator
, optional) — Atorch.Generator
to make generation deterministic. - num_inference_steps (
int
, optional, defaults to 250) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. - output_type (
str
, optional, defaults to"pil"
) — The output format of the generated image. Choose betweenPIL.Image
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a ImagePipelineOutput instead of a plain tuple.
Returns
ImagePipelineOutput or tuple
If return_dict
is True
, ImagePipelineOutput is returned, otherwise a tuple
is
returned where the first element is a list with the generated images
The call function to the pipeline for generation.
Examples:
>>> from diffusers import DiTPipeline, DPMSolverMultistepScheduler
>>> import torch
>>> pipe = DiTPipeline.from_pretrained("facebook/DiT-XL-2-256", torch_dtype=torch.float16)
>>> pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
>>> pipe = pipe.to("cuda")
>>> # pick words from Imagenet class labels
>>> pipe.labels # to print all available words
>>> # pick words that exist in ImageNet
>>> words = ["white shark", "umbrella"]
>>> class_ids = pipe.get_label_ids(words)
>>> generator = torch.manual_seed(33)
>>> output = pipe(class_labels=class_ids, num_inference_steps=25, generator=generator)
>>> image = output.images[0] # label 'white shark'
get_label_ids
< source >( label: Union ) → list
of int
Map label strings from ImageNet to corresponding class ids.
ImagePipelineOutput
class diffusers.ImagePipelineOutput
< source >( images: Union )
Output class for image pipelines.