- 本项目旨在以 Toy Demo😄😄的方式实现经典的 AIGC⚡⚡生成模型,避免下载复杂的数据集和需使用高端 GPU 的问题。
- 通过直达模型🔭🔭的核心代码(配合论文阅读更佳),学习模型的核心**,达到快速入门学习的目的。
- 以下均为个人入门学习 AIGC 所阅读和编写的部分代码(持续更新✨✨!!!),欢迎指出问题和 Pull Request👯👯(PR)。
- 以下均为个人入门学习 AIGC 所阅读的优秀博客📕📕和经典论文📕📕,感谢所有作者的贡献✨✨✨✨!!
- A simple demo about DDPM in the DDPM folder.
- A simple demo about GAN in the GAN folder.
- A simple demo about VAE in the VAE folder.
- A simple demo about VQVAE in the VQVAE folder.
- A simple demo about PixelCNN and VQVAE in the PixelCNN_VQVAE folder.
- A simple demo about Autoregressive Transformer and VQVAE in the AR_VQVAE folder.
- A simple demo about Conditional Autoregressive Transformer in the Cond_AR_Transformer folder.
- A simple demo about Calculating Motion FID in the Cal_Motion_FID folder.
- A simple demo about Conditional Diffusion Using Classifier-Free Diffusion Guidance in the Cond_diffusion_Free_guide folder.
- A simple demo about Using Diffuser in the Diffuser_pipeline folder.
- A simple demo about Using LoRA based on the PEFT in the PEFT_LoRA folder.
- A simple demo about MoE Model in the Simple_MoE folder.
- A simple demo about DDIM Model in the Simple_DDIM folder.
- A simple demo about UNet Model of Stable Diffusion in the SD_UNet folder.
- A simple demo about U-ViT Demo in the Simple_U-DiT folder.
- A simple demo about DDIM of Stable Diffusion in the SD_DDIM folder.
- A simple demo about Inpainting of Stable Diffusion in the SD_Inpainting folder.
- A simple demo about Classifer Guidance in the Simple_Classifer_Guide folder.
- DDPM = 拆楼 + 建楼
- 一文带你看懂DDPM和DDIM
- 通俗理解GAN
- DiT详解
- 变分自编码器
- 变分自编码器
- 轻松理解 VQ-VAE
- 文生图模型之Stable Diffusion
- LoRA 在 Stable Diffusion 中的三种应用
- 扩散模型中的v-prediction
- 深入浅出完整解析ControlNet
- Stable Diffusion 原理介绍
- 一文读懂DDIM凭什么可以加速DDPM的采样效率
- 自回归图像生成代码阅读:VQ-GAN
- 详解VQGAN(一)| 结合离散化编码与Transformer的百万像素图像生成
- 保持ID的人像生成技术介绍:IP-Adaptor,PhotoMaker,InstantID
- Classifier Guidance 和 Classifier Free Guidance
- SD和Sora们背后的关键技术!一文搞懂所有 VAE 模型(4个AE+12个VAE原理汇总)
- AIGC专栏4——Stable Diffusion原理解析-inpaint修复图片为例
- AIGC-Stable Diffusion之Inpaint(图像修复)
- [论文理解] Classifier-free diffusion guidance
- Stable Video Diffusion 结构浅析与论文速览
- Stable Video Diffusion 源码解读 (Diffusers 版)
- AIGC-Stable Diffusion之VAE
- 深入浅出完整解析Stable Diffusion XL(SDXL)核心基础知识
- Rich Human Feedback for Text-to-Image Generation (CVPR 2024 best paper) [Paper] [Code]
- Generative Image Dynamics (CVPR 2024 best paper) [Paper] [Project]
- Denoising Diffusion Probabilistic Models [Paper] [Code]
- DENOISING DIFFUSION IMPLICIT MODELS [Paper] [Code]
- High-Resolution Image Synthesis with Latent Diffusion Models [Paper] [Code] [Code]
- Diffusion Models Beat GANs on Image Synthesis [Paper] [Code]
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets [Paper] [Code]
- Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models [Paper]
- Elucidating the Design Space of Diffusion-Based Generative Models [Paper]
- Autoregressive Image Generation without Vector Quantization [Paper]
- Neural Discrete Representation Learning [Paper]
- Auto-Encoding Variational Bayes [Paper]
- CV-VAE: A Compatible Video VAE for Latent Generative Video Models [Paper] [Code]
- Taming Transformers for High-Resolution Image Synthesis [Paper] [Code]
- Scalable Diffusion Models with Transformers [Paper] [Code]
- Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding [Paper] [Code]
- All are Worth Words: A ViT Backbone for Diffusion Models [Paper] [Code]
- stable-diffusion [Code]
- ControlNet [Code]
- AnimateDiff [Code]
- Open-Sora [Code]
- Open-Sora-Plan [Code]
- VAR [Code]
- IC-Light [Code]
- IP-Adapter [Code]
- LivePortrait [Code]
- zero123 [Code]
- VideoTetris [Code]
Thanks to all the authors of the above blogs and papers!!