Tony-Lowe

brush-your-text

ShiArthur03

EAST

EAST: An Efficient and Accurate Scene Text Detector.

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

MIGC

[CVPR 2024 Highlight] "MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis" (Official Implementation)

PCIG

diffusion_reward

[ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"

interactdiffusion

[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".

Q-DiT

PyTorch code for Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

Six-CD

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models

bioclip

This is the repository for the BioCLIP model and the TreeOfLife-10M dataset [CVPR'24 Oral, Best Student Paper].

geneval

GenEval: An object-focused framework for evaluating text-to-image alignment

mmdit

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

SimpleTuner

A general fine-tuning kit geared toward Stable Diffusion 2.1, Stable Diffusion 3, DeepFloyd, and SDXL.

cutlass

CUDA Templates for Linear Algebra Subroutines

make-it-count

Official implemention of "Make It Count: Text-to-Image Generation with an Accurate Number of Objects"

VideoTetris

VideoTetris: Towards Compositional Text-To-Video Generation

llama

Inference code for Llama models

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Omost

Your image is almost there!

PatchScaler

PatchScaler: An Efficient Patch-independent Diffusion Model for Super-Resolution

LOVA3

The official repo of "Learning to Visual Question Answering, Asking and Assessment"

MoRA

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

DMD2

EditWorld

EditWorld: Simulating World Dynamics for Instruction-Following Image Editing

Diff-BGM

official code for CVPR'24 paper Diff-BGM

ViViD

ViViD: Video Virtual Try-on using Diffusion Models

fast-kan

FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)

Efficient-Vision-Language-Pre-training-by-Cluster-Masking

[CVPR 2024] Improving language-visual pretraining efficiency by perform cluster-based masking on images.

ContextDiff

[ICLR 2024] Contextualized Diffusion Models for Text-Guided Image and Video Generation