Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"

⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Implementation of "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning"

Official repo for consistency models.

Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)

Code for Shifted Diffusion for Text-to-image Generation (CVPR 2023)

Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

Let us control diffusion models!

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

High-Resolution Image Synthesis with Latent Diffusion Models

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…

stable diffusion training

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Paper implementations from scratch and machine learning tutorials

Code for paper LAFITE: Towards Language-Free Training for Text-to-Image Generation (CVPR 2022)

Tensorflow implementation of "Tackling the Generative Learning Trilemma with Denoising Diffusion GANs" (ICLR 2022 Spotlight)

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

High-Resolution Image Synthesis with Latent Diffusion Models

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Official implementation of "DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents"

The Official PyTorch Implementation of "VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models" (ICLR 2021 spotlight paper)