Stars
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.
Simple and readable code for training and sampling from diffusion models
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
ConceptAttention: A method for interpreting multi-modal diffusion transformers.
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
Sparsify transformers with SAEs and transcoders
Interactive visualizations of the geometric intuition behind diffusion models.
ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.
LLM Self Defense: By Self Examination, LLMs know they are being tricked
ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).
Dataset of prompts, synthetic AI generated images, and aesthetic ratings.
Flax is a neural network library for JAX that is designed for flexibility.
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)
[ICCV 2023] Consistent Image Synthesis and Editing
Huggingface-compatible SDXL Unet implementation that is readily hackable
[CVPR 2024] Official implementation of the paper "Visual In-context Learning"
Physics simulation plugin of Manim that can generate scenes in various branches of Physics.
A prompting enhancement library for transformers-type text embedding systems
ComfyUI custom nodes for inpainting/outpainting using the new latent consistency model (LCM)
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
App showcasing multiple real-time diffusion models pipelines with Diffusers
Davidsonian Scene Graph (DSG) for Text-to-Image Evaluation (ICLR 2024)
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)