Diffusion 일기장
-
in diffusers/examples/text_to_image 디렉토리
-
Training
accelerate launch train_text_to_image_lora_sdxl.py --pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" --pretrained_vae_model_name_or_path="madebyollin/sdxl-vae-fp16-fix" --dataset_name="AdamLucek/oldbookillustrations-small" --validation_prompt="An inventor tinkers with a complex machine in his workshop, oblivious to the setting sun outside" --num_validation_images=4 --validation_epochs=1 --output_dir="output" --resolution=1024 --center_crop --random_flip --train_text_encoder --train_batch_size=1 --num_train_epochs=10 --checkpointing_steps=500 --gradient_accumulation_steps=4 --learning_rate=1e-04 --lr_warmup_steps=0 --report_to="wandb" --dataloader_num_workers=8 --allow_tf32 --mixed_precision="fp16" --hub_model_id="sdxl-lora-testing"
- Inference jupyter
ratsgo's blog
딥러닝 기초 내용들 참고하기 좋은 블로그
[Link]
gaussian37
Computer Vision 기초 내용
[Link]
What are Diffusion Models?
Diffusion 기초, 전반적인 내용 정리
[Link]
How Diffusion Models work: the math from scratch
Diffusion 기초, 전반적인 내용 정리2
[Link]
DDPM Paper review
DDPM 논문 리뷰 블로그
[Link]
Diffusion 논문 리뷰
Diffusion 필수 논문 리뷰 영상
[Youtube1]
[Youtube2]
[Youtube3]
Denoising Diffusion Probabilistic Models ✔️
NeurIPS 2020. [Paper] [Github]
Jonathan Ho, Ajay Jain, Pieter Abbeel
19 Jun 2020
Denoising Diffusion Implicit Models ✔️
ICLR 2021. [Paper Github]
Jiaming Song, Chenlin Meng, Stefano Ermon
Standford University
6 Oct 2020
Diffusion Models Beat GANs on Image Synthesis ✔️
arXiv 2021. [Paper] [Github]
Prafulla Dhariwal, Alex Nichol
OpenAI
11 May 2021
Generative Modeling by Estimating Gradients of the Data Distribution
NeurIPS 2019. [Paper] [Github]
Yang Song, Stefano Ermon
12 Jul 2019
Score-Based Generative Modeling through Stochastic Differential Equations ✔️
ICLR 2021. [Paper] [Github]
Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Stanford University | Google Brain
26 Nov 2020
Classifier-Free Diffusion Guidance
NeurIPS Workshop 2021. [Paper]
Jonathan Ho, Tim Salimans
Google Research, Brain team
28 Sep 2021
Diffusion-GAN: Training GANs with Diffusion
arXiv 2022. [Paper]
Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou
The University of Texas at Austin | Microsoft Azure AI
11 Oct 2022
Improved Denoising Diffusion Probabilistic Models
ICLR 2021. [Paper] [Github]
Alex Nichol, Prafulla Dhariwal
OpenAI
18 Feb 2021
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs ✔️
ICLR 2022. [Paper] [Page] [Github]
Zhisheng Xiao, Karsten Kreis, Arash Vahdat
The University of Chicago | NVIDIA
15 Dec 2021
High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion) ✔️
arXiv 2021. [Paper] [Github]
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer
Ludwig Maximilian University of Munich & IWR, Heidelberg University, Germany | Runway ML
20 Dec 2021
Video Diffusion Models ✔️
arXiv 2022. [Paper] [Github]
Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, David J. Fleet
Google Research, Brain Team
7 Apr 2022
Diffusion Models for Video Prediction and Infilling ✔️
TMLR 2022. [Paper] [Github]
Tobias Höppe, Arash Mehrjou, Stefan Bauer, Didrik Nielsen, Andrea Dittadi
15 Jun 2022
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation ✔️
NeurIPS 2022. [Paper] [Github]
Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal
19 May 2022
Repaint: RePaint: Inpainting using Denoising Diffusion Probabilistic Models ✔️
CVPR 2022. [Paper] [Github]
Andreas Lugmayr, Martin Danelljan, Andres Romero, Fisher Yu, Radu Timofte, Luc Van Gool
Computer Vision Lab, ETH Zurich, Switzerland
24 Jan 2022
DDPM 기초 구현
[Youtube]
Diffusion Huggingface
[Colab]