The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)

COCO Stuff API

The official homepage of the COCO-Stuff dataset.

Quick scripts to calculate CLIP text-image similarity

Compute FID scores with PyTorch.

[WACV 2024] Training-Free Layout Control with Cross-Attention Guidance

[Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis

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

🤗 Unofficial huggingface/diffusers-based implementation of the paper "Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis".

Dataset splits and evaluation code for the paper "Benchmark for Compositional Text-to-Image Synthesis" (NeurIPS 2021)

Consistency Distilled Diff VAE