ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models
This addresses the problem of generating semantically desired images in diffusion models for researchers and practitioners in image generation, offering a novel conditioning approach without retraining.
The authors tackled the challenge of controlling image generation in denoising diffusion probabilistic models (DDPM) by proposing ILVR, a method that guides the process using a reference image, enabling high-quality image generation with controllability across tasks like image translation and editing.
Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process in DDPM, it is challenging to generate images with the desired semantics. In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image. Here, the refinement of the generative process in DDPM enables a single DDPM to sample images from various sets directed by the reference image. The proposed ILVR method generates high-quality images while controlling the generation. The controllability of our method allows adaptation of a single DDPM without any additional learning in various image generation tasks, such as generation from various downsampling factors, multi-domain image translation, paint-to-image, and editing with scribbles.