WuyangLuo

Qwen2-VL

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Optimization-Theory-and-Algorithm

用于存放《最优化理论与算法》代码与课件

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

SEED-X

Multimodal Models in Real World

HQ-Edit

HQ-Edit: A High-Quality and High-Coverage Dataset for General Image Editing

LAION-Face

The human face subset of LAION-400M for large-scale face pretraining.

BlendGAN

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

InstantID

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

blended-latent-diffusion

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

generative-models

Generative Models by Stability AI

erasing

Erasing Concepts from Diffusion Models

instruct-pix2pix

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

awesome-diffusion-categorized

collection of diffusion model papers categorized by their subareas

SIEDOB

RefFaceInpainting

prompt-to-prompt

PAIR-Diffusion

[CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

FreGAN_NeurIPS2022

[NeurIPS2022] FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

ECCV2022_WaveGAN

The official code of WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation (ECCV2022)

ControlNet

Let us control diffusion models!

google-research

Google Research

ETC-Real-time-Per-frame-Semantic-video-segmentation

Enforcing temporal consistency in real-time per-frame semantic video segmentation

SPMPGAN

imaginaire

NVIDIA's Deep Imagination Team's PyTorch Library