A latent text-to-image diffusion model

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Google Brain AutoML

Kandinsky 2 — multilingual text2image latent diffusion model

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

Stable Diffusion implemented from scratch in PyTorch

Dataset to assess the disentanglement properties of unsupervised learning methods

[ECCV 2022] Compositional Generation using Diffusion Models

Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

An implementation of the Prompt-to-Prompt paper for the SDXL architecture

Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"