mihirp1998/AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
Language: Python
#alignment #diffusion_models #reinforcement_learning #stable_diffusion #text_to_image
Stars: 104 Issues: 4 Forks: 1
https://github.com/mihirp1998/AlignProp

hustvl/GaussianDreamer
GaussianDreamer: Fast Generation from Text to 3D Gaussian Splatting with Point Cloud Priors
Language: Python
#aigc #computer_vision #diffusion_models #dreamfusion #gaussian_splatting #nerf #radiance_field #text_to_3d
Stars: 134 Issues: 0 Forks: 1
https://github.com/hustvl/GaussianDreamer

deepseek-ai/DreamCraft3D
Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
#3d_creation #3d_generation #aigc #diffusion_models #generative_model #image_to_3d
Stars: 304 Issues: 3 Forks: 4
https://github.com/deepseek-ai/DreamCraft3D

horseee/DeepCache
DeepCache: Accelerating Diffusion Models for Free
Language: Python
#diffusion_models #efficient_inference #model_compression #stable_diffusion #training_free
Stars: 177 Issues: 5 Forks: 5
https://github.com/horseee/DeepCache

FoundationVision/VAR
[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction"
Language: Python
#auto_regressive_model #diffusion_models #image_generation #transformers
Stars: 440 Issues: 6 Forks: 10
https://github.com/FoundationVision/VAR

PKU-YuanGroup/MagicTime
MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
Language: Python
#diffusion_models #long_video_generation #metamorphic_video_generation #open_sora_plan #text_to_video #time_lapse #time_lapse_dataset #video_generation
Stars: 281 Issues: 4 Forks: 16
https://github.com/PKU-YuanGroup/MagicTime

jy0205/Pyramid-Flow
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
Language: Python
#diffusion_models #flow_matching #video_generation
Stars: 613 Issues: 10 Forks: 47
https://github.com/jy0205/Pyramid-Flow

mit-han-lab/nunchaku
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Language: Cuda
#diffusion_models #flux #genai #lora #mlsys #quantization
Stars: 249 Issues: 10 Forks: 13
https://github.com/mit-han-lab/nunchaku

Lightricks/LTX-Video
Official repository for LTX-Video
Language: Python
#diffusion_models #dit #image_to_video #image_to_video_generation #text_to_video #text_to_video_generation
Stars: 241 Issues: 8 Forks: 9
https://github.com/Lightricks/LTX-Video

Lightricks/ComfyUI-LTXVideo
LTX-Video Support for ComfyUI
Language: Python
#comfyui #diffusion_models #dit #image_to_video #image_to_video_generation #text_to_image #text_to_image_generation
Stars: 217 Issues: 18 Forks: 9
https://github.com/Lightricks/ComfyUI-LTXVideo

TencentARC/BrushEdit
The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"
Language: Python
#diffusion_models #image_editing #image_inpainting
Stars: 262 Issues: 4 Forks: 12
https://github.com/TencentARC/BrushEdit

baaivision/NOVA
NOVA: Autoregressive Video Generation without Vector Quantization
Language: Python
#autoregressive_models #diffusion_models #image_generation #video_generation
Stars: 145 Issues: 1 Forks: 2
https://github.com/baaivision/NOVA

Tencent/HunyuanVideo-I2V
HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo
Language: Python
#diffusion_models #image_to_video #image_to_video_generation #videogeneration
Stars: 646 Issues: 12 Forks: 32
https://github.com/Tencent/HunyuanVideo-I2V

SandAI-org/MAGI-1
MAGI-1: Autoregressive Video Generation at Scale
Language: Python
#autoregressive #diffusion_models #video_generation
Stars: 911 Issues: 7 Forks: 32
https://github.com/SandAI-org/MAGI-1

River-Zhang/ICEdit
Repository for paper "In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer"
Language: Python
#diffusion #diffusion_models #diffusion_transformer #dit #editing_image #image_editing #in_context
Stars: 136 Issues: 1 Forks: 3
https://github.com/River-Zhang/ICEdit

Tencent/HunyuanCustom
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Language: Python
#audio_driven #diffusion_models #image_to_video #image_to_video_generation #video_editing #video_generation
Stars: 360 Issues: 4 Forks: 14
https://github.com/Tencent/HunyuanCustom