Awesome MindDiffusion Models

Introduction

This repo is an open source collection of a series of classic and new SoTA diffusion models based on MindSpore. We also provide the awesome list of diffusion models.

Released now

These models are implemented in MindSpore and run on Ascend.

Model Name	Task	Link
Taichu-GLIDE	Vision - Text To Image	Link
Wukong-Huahua	Vision - Text To Image	Link
Stable-Diffusionv2	Vision - Text To Image	Link

Awesome Model List

Model	Paper	Institution	Date	Conference	Support
DDPM	DDPM: Denoising Diffussion Probalisitic Model	UC Berkeley	Jun 2020	NeurIPS 2020	To do
Vision - Image generation
Improved diffusion	Improved Denoising Diffusion Probabilistic Models	OpenAI	Feb 2021	PMLR 2021
Guided diffusion	Diffusion Models Beat Gans on Image Synthesis	OpenAI	Apr 2021	NeurIPS 2021
ADM	Diffusion Models Beat GANs on Image Synthesis	OpenAI	Apr 2021	NeurIPS 2021
FastDPM	On Fast Sampling of Diffusion Probabilistic Models	NVIDIA	May 2021	ICLR Workshop 2021
LSGM	Score-based Generative Modeling in Latent Space	NVIDIA	Jun 2021	NeurIPS 2021
Distilled-DM	Progressive Distillation for Fast Sampling of Diffusion Models	Google Brain	Feb 2022	ICLR 2022
GGDM	Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality	Google Brain	Feb 2022	ICLR 2022
Vision - Text to Image
Stable Diffusion/LDM	High-Resolution Image Synthesis with Latent Diffusion Models	Stability.AI	Dec 2021
Glide	Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models	OpenAI	Dec 2021
Dalle-2	Hierarchical Text-conditional Image Generation with Clip Latents	OpenAI	Apr 2022
KNN Diffusion	Image Generation via Large-Scale Retrieval	Meta AI	Apr 2022
Imagen	Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding	Google Brain	May 2022
LAION-RDM	Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models	Ludwig-Maximilian University of Munich	Jul 2022
DreamBooth	DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation	Google Research	Aug 2022
DreamFusion	DreamFusion: Text-to-3D using 2D Diffusion	Google Research	29 Sep 2022
Vision - Image Editing
SDEdit	SDEdit: Image Synthesis and Editing with Stochastic Differential Equations	Stanford U & CMU	Aug 2021	ICLR 2022
RePaint	RePaint: Inpainting using Denoising Diffusion Probabilistic Models	ETH Zurich	Jan 2022	CVPR 2022
Vision - Video Genereation
Video diffusion models	Video diffusion models	Google Brain	Apr 2022	ICLR 2022 Workshop
MCVD	MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation	University of Montreal	May 2022
Make-A-Video	Make-A-Video: Text-to-Video Generation without Text-Video Data	Meta AI	29 Sep 2022
Imagen Video	Imagen Video: High Definition Video Generation with Diffusion Models	Google Brain	5 Oct 2022
Natural language
Diffusion-LM	Diffusion-LM Improves Controllable Text Generation	Stanford University	May 2022
Audio - Audio Generation
DiffWave	DiffWave: A Versatile Diffusion Model for Audio Synthesis	Nvidia & Baidu	Jun 2020	ISMIR 2021
WaveGrad	WaveGrad: Estimating Gradients for Waveform Generation	Google Brain	Sep 2020	ICLR 2021
Symbolic Music Generation	Symbolic Music Generation with Diffusion Models	Google Brain	Mar 2021	ISMIR 2021
DiffSinger	DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism	Zhejiang University	May 2021	AAAI 2022
VDM	Variational Diffusion Models	Google Brain	Jul 2021	NeurIPS 2021
FastDiff	FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis	Tencent AI Lab	Apr 2022	IJCAI 2022
BDDMs	BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis	Tencent AI Lab	May 2022	ICLR 2022
SawSing	DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation		AUG 2022	ISMIR 2022
Prodiff	ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech	Zhejiang University	JUL 2022	ACM Multimedia 2022
Audio - Audio Conversion
DiffVC	Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme	Huawei Noah	Sep 2021	ICLR 2022
Audio - Audio Enhancement
NU-Wave	NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling	MINDSLAB	Apr 2021	Interspeech 2021
CDiffSE	Conditional Diffusion Probabilistic Model for Speech Enhancement	CMU	Feb 2022	IEEE 2022
Audio - Text to Speech
Grad-TTS	Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech	Huawei Noah	May 2021
EdiTTS	EdiTTS: Score-based Editing for Controllable Text-to-Speech	Yale University	Oct 2021
DiffGAN-TTS	DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs	Tencent AI Lab	Jan 2022
Diffsound	Diffsound: Discrete Diffusion Model for Text-to-sound Generation	Tencent AI Lab	Jul 2022

Contributing

We welcom all contributions to improve this project! Please fork this repo and submit a pull request to contribute your diffusion models.