YqGao716

Attend-and-Excite

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

attention-refocusing

BoxDiff

[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

consistencydecoder

Consistency Distilled Diff VAE

custom-diffusion

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

daam

Diffusion attentive attribution maps for interpreting Stable Diffusion.

DenseDiffusion

diffusion-classifier

Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training

Energy-Based-CrossAttention

The official repository of "Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models".

FreeU

FreeU: Free Lunch in Diffusion U-Net

IF

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

LLaMA-Adapter

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

MasaCtrl

Consistent Image Synthesis and Editing, ICCV 2023

MiniGPT-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

MultiDiffusion

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

photoswap

Official implementation of the paper "Photoswap: Personalized Subject Swapping in Images"

pnp-diffusers

ProSpect

Official implementation of the paper "ProSpect: Expanded Conditioning for the Personalization of Attribute-aware Image Generation"

rich-text-to-image

Rich-Text-to-Image Generation

SEARLE

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

SEED

Empowers LLMs with the ability to see and draw.

SHIP

Official code for ICCV 2023 paper, "Improving Zero-Shot Generalization for CLIP with Synthesized Prompts"

Syntax-Guided-Generation

T2I-CompBench

TheChosenOne

Unofficial implementation of the paper "The Chosen One: Consistent Characters in Text-to-Image Diffusion Models"

tifa

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

TOAST

Official code for "Refocusing Is Key to Transfer Learning"