ReNoise: Real Image Inversion Through Iterative Noising
Abstract
Recent advancements in text-guided diffusion models
have unlocked powerful image manipulation capabilities.
However, applying these methods to real images necessitates the inversion of the images into the domain of the
pretrained diffusion model. Achieving faithful inversion remains a challenge, particularly for models trained to generate images with a small number of denoising steps. In
this work, we present an inversion method which offers a
good balance between accuracy and speed. Building on
reversing the diffusion sampling process, our method employs an iterative ReNoising mechanism at each inversion
sampling step. This mechanism refines the approximation
of a predicted point along the forward diffusion trajectory,
by iteratively applying the pretrained diffusion model, and
averaging these predictions. We evaluate the performance
of our ReNoising technique using various sampling algorithms and models, including recent accelerated diffusion
models. Through comprehensive evaluations and comparisons, we show its effectiveness in terms of both accuracy
and speed. Furthermore, we confirm that our method preserves editability by demonstrating text-driven image editing on real images.
have unlocked powerful image manipulation capabilities.
However, applying these methods to real images necessitates the inversion of the images into the domain of the
pretrained diffusion model. Achieving faithful inversion remains a challenge, particularly for models trained to generate images with a small number of denoising steps. In
this work, we present an inversion method which offers a
good balance between accuracy and speed. Building on
reversing the diffusion sampling process, our method employs an iterative ReNoising mechanism at each inversion
sampling step. This mechanism refines the approximation
of a predicted point along the forward diffusion trajectory,
by iteratively applying the pretrained diffusion model, and
averaging these predictions. We evaluate the performance
of our ReNoising technique using various sampling algorithms and models, including recent accelerated diffusion
models. Through comprehensive evaluations and comparisons, we show its effectiveness in terms of both accuracy
and speed. Furthermore, we confirm that our method preserves editability by demonstrating text-driven image editing on real images.
