DiffCollage: Parallel Generation of Large Content with Diffusion Models

by   Qinsheng Zhang, et al.

We present DiffCollage, a compositional diffusion model that can generate large content by leveraging diffusion models trained on generating pieces of the large content. Our approach is based on a factor graph representation where each factor node represents a portion of the content and a variable node represents their overlap. This representation allows us to aggregate intermediate outputs from diffusion models defined on individual nodes to generate content of arbitrary size and shape in parallel without resorting to an autoregressive generation procedure. We apply DiffCollage to various tasks, including infinite image generation, panorama image generation, and long-duration text-guided motion generation. Extensive experimental results with a comparison to strong autoregressive baselines verify the effectiveness of our approach.


page 18

page 19

page 20

page 21

page 31

page 32

page 33

page 34


Diffusion idea exploration for art generation

Cross-Modal learning tasks have picked up pace in recent times. With ple...

Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation

The integration of Vector Quantised Variational AutoEncoder (VQ-VAE) wit...

Drag-guided diffusion models for vehicle image generation

Denoising diffusion models trained at web-scale have revolutionized imag...

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

Autoregressive models for text sometimes generate repetitive and low-qua...

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

Despite the remarkable performance of text-to-image diffusion models in ...

Accuracy and Fidelity Comparison of Luna and DALL-E 2 Diffusion-Based Image Generation Systems

We qualitatively examine the accuracy and fideltiy between two diffusion...

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC

Since their introduction, diffusion models have quickly become the preva...

Please sign up or login with your details

Forgot password? Click here to reset