Authors:
(1) Dustin Podell, Stability AI, Applied Research;
(2) Zion English, Stability AI, Applied Research;
(3) Kyle Lacey, Stability AI, Applied Research;
(4) Andreas Blattmann, Stability AI, Applied Research;
(5) Tim Dockhorn, Stability AI, Applied Research;
(6) Jonas Müller, Stability AI, Applied Research;
(7) Joe Penna, Stability AI, Applied Research;
(8) Robin Rombach, Stability AI, Applied Research. Table of Links Abstract and 1 Introduction 2 Improving Stable Diffusion 2.1 Architecture & Scale 2.2 Micro-Conditioning 2.3 Multi-Aspect Training 2.4 Improved Autoencoder and 2.5 Putting Everything Together 3 Future Work Appendix A Acknowledgements B Limitations C Diffusion Models D Comparison to the State of the Art E Comparison to Midjourney v5.1 F On FID Assessment of Generative Text-Image Foundation Models G Additional Comparison between Single- and Two-Stage SDXL pipeline References 2.1 Architecture & Scale Starting with the seminal works Ho et al. [14] and Song et al. [47], which demonstrated that DMs are powerful generative models for image synthesis, the convolutional UNet [39] architecture has been the dominant architecture for diffusion-based image synthesis. However, with the development of foundational DMs [40, 37, 38], the underlying architecture has constantly evolved: from adding self-attention and improved upscaling layers [5], over cross-attention for text-to-image synthesis [38], to pure transformer-based architectures [33]. We follow this trend and, following Hoogeboom et al. [16], shift the bulk of the transformer computation to lower-level features in the UNet. In particular, and in contrast to the original Stable Diffusion architecture, we use a heterogeneous distribution of transformer blocks within the UNet: For efficiency reasons, we omit the transformer block at the highest feature level, use 2 and 10 blocks at the lower levels, and remove the lowest level (8× downsampling) in the UNet altogether — see Tab. 1 for a comparison between the architectures of Stable Diffusion 1.x & 2.x and SDXL. We opt for a more powerful pre-trained text encoder that we use for text conditioning. Specifically, we use OpenCLIP ViT-bigG [19] in combination with CLIP ViT-L [34], where we concatenate the penultimate text encoder outputs along the channel-axis [1]. Besides using cross-attention layers to condition the model on the text-input, we follow [30] and additionally condition the model on the pooled text embedding from the OpenCLIP model. These changes result in a model size of 2.6B parameters in the UNet, see Tab. 1. The text encoders have a total size of 817M parameters. This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Dustin Podell, Stability AI, Applied Research; (2) Zion English, Stability AI, Applied Research; (3) Kyle Lacey, Stability AI, Applied Research; (4) Andreas Blattmann, Stability AI, Applied Research; (5) Tim Dockhorn, Stability AI, Applied Research; (6) Jonas Müller, Stability AI, Applied Research; (7) Joe Penna, Stability AI, Applied Research; (8) Robin Rombach, Stability AI, Applied Research. Authors: Authors: (1) Dustin Podell, Stability AI, Applied Research; (2) Zion English, Stability AI, Applied Research; (3) Kyle Lacey, Stability AI, Applied Research; (4) Andreas Blattmann, Stability AI, Applied Research; (5) Tim Dockhorn, Stability AI, Applied Research; (6) Jonas Müller, Stability AI, Applied Research; (7) Joe Penna, Stability AI, Applied Research; (8) Robin Rombach, Stability AI, Applied Research. Table of Links Abstract and 1 Introduction Abstract and 1 Introduction 2 Improving Stable Diffusion 2 Improving Stable Diffusion 2.1 Architecture & Scale 2.1 Architecture & Scale 2.2 Micro-Conditioning 2.2 Micro-Conditioning 2.3 Multi-Aspect Training 2.3 Multi-Aspect Training 2.4 Improved Autoencoder and 2.5 Putting Everything Together 2.4 Improved Autoencoder and 2.5 Putting Everything Together 3 Future Work 3 Future Work Appendix Appendix A Acknowledgements A Acknowledgements B Limitations B Limitations C Diffusion Models C Diffusion Models D Comparison to the State of the Art D Comparison to the State of the Art E Comparison to Midjourney v5.1 E Comparison to Midjourney v5.1 F On FID Assessment of Generative Text-Image Foundation Models F On FID Assessment of Generative Text-Image Foundation Models G Additional Comparison between Single- and Two-Stage SDXL pipeline G Additional Comparison between Single- and Two-Stage SDXL pipeline References References 2.1 Architecture & Scale Starting with the seminal works Ho et al. [14] and Song et al. [47], which demonstrated that DMs are powerful generative models for image synthesis, the convolutional UNet [39] architecture has been the dominant architecture for diffusion-based image synthesis. However, with the development of foundational DMs [40, 37, 38], the underlying architecture has constantly evolved: from adding self-attention and improved upscaling layers [5], over cross-attention for text-to-image synthesis [38], to pure transformer-based architectures [33]. We follow this trend and, following Hoogeboom et al. [16], shift the bulk of the transformer computation to lower-level features in the UNet. In particular, and in contrast to the original Stable Diffusion architecture, we use a heterogeneous distribution of transformer blocks within the UNet: For efficiency reasons, we omit the transformer block at the highest feature level, use 2 and 10 blocks at the lower levels, and remove the lowest level (8× downsampling) in the UNet altogether — see Tab. 1 for a comparison between the architectures of Stable Diffusion 1.x & 2.x and SDXL. We opt for a more powerful pre-trained text encoder that we use for text conditioning. Specifically, we use OpenCLIP ViT-bigG [19] in combination with CLIP ViT-L [34], where we concatenate the penultimate text encoder outputs along the channel-axis [1]. Besides using cross-attention layers to condition the model on the text-input, we follow [30] and additionally condition the model on the pooled text embedding from the OpenCLIP model. These changes result in a model size of 2.6B parameters in the UNet, see Tab. 1. The text encoders have a total size of 817M parameters. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Improving Stable Diffusion Architecture

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Additional Comparison between Single- and Two-Stage SDXL pipeline

How to Develop Data-Driven AI Apps: A Guide to Making AI Services Directly From the Database

Building Multimodal Generative AI Systems: Architecture, Refinement, and Enhancement

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Modular Enhancements for Stable Diffusion Architecture

Micro-Conditioning Strategies for Superior Image Generation in SDXL

Additional Comparison between Single- and Two-Stage SDXL pipeline

How to Develop Data-Driven AI Apps: A Guide to Making AI Services Directly From the Database

Building Multimodal Generative AI Systems: Architecture, Refinement, and Enhancement

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Modular Enhancements for Stable Diffusion Architecture

Micro-Conditioning Strategies for Superior Image Generation in SDXL

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps