DDIMScheduler

Denoising Diffusion Implicit Models (DDIM) by Jiaming Song, Chenlin Meng and Stefano Ermon.

The abstract from the paper is:

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose reverse process can be much faster to sample from. We empirically demonstrate that DDIMs can produce high quality samples 10× to 50× faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample quality, and can perform semantically meaningful image interpolation directly in the latent space.

The original codebase of this paper can be found at ermongroup/ddim, and you can contact the author on tsong.me.

Tips

The paper Common Diffusion Noise Schedules and Sample Steps are Flawed claims that a mismatch between the training and inference settings leads to suboptimal inference generation results for Stable Diffusion. To fix this, the authors propose:

[!WARNING] 🧪 This is an experimental feature!

1. rescale the noise schedule to enforce zero terminal signal-to-noise ratio (SNR)

pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, rescale_betas_zero_snr=True)

1. train a model with v_prediction (add the following argument to the train_text_to_image.py or train_text_to_image_lora.py scripts)

--prediction_type="v_prediction"

1. change the sampler to always start from the last timestep

pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config, timestep_spacing="trailing")

1. rescale classifier-free guidance to prevent over-exposure

image = pipe(prompt, guidance_rescale=0.7).images[0]

For example:

from diffusers import DiffusionPipeline, DDIMScheduler
import torch

pipe = DiffusionPipeline.from_pretrained("ptx0/pseudo-journey-v2", torch_dtype=torch.float16)
pipe.scheduler = DDIMScheduler.from_config(
    pipe.scheduler.config, rescale_betas_zero_snr=True, timestep_spacing="trailing"
)
pipe.to("cuda")

prompt = "A lion in galaxies, spirals, nebulae, stars, smoke, iridescent, intricate detail, octane render, 8k"
image = pipe(prompt, guidance_rescale=0.7).images[0]
image

DDIMScheduler

[[autodoc]] DDIMScheduler

DDIMSchedulerOutput

[[autodoc]] schedulers.scheduling_ddim.DDIMSchedulerOutput