Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024
| Date | Stars |
|---|---|
| 2026-07-31 | 355 |
| 2026-08-05 | 354 |
| 2026-08-06 | 354 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Smooth Diffusion This repository is the official Pytorch implementation for [Smooth Diffusion](https://arxiv.org/abs/2312.04410). [](https://huggingface.co/spaces/shi-labs/Smooth-Diffusion) [](https://shi-labs.github.io/Smooth-Diffusion/) [](https://arxiv.org/abs/2312.04410) > **Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models** > [Jiayi Guo](https://www.jiayiguo.net)\*, > [Xingqian Xu](https://www.linkedin.com/in/xingqian-xu-97b46526/)\*, > [Yifan Pu](https://scholar.google.com/citations?user=oM9rnYQAAAAJ&hl=en), > [Zanlin Ni](https://scholar.google.com/citations?user=Yibz_asAAAAJ&hl=en), > [Chaofei Wang](https://scholar.google.com/citations?user=-hwGMHcAAAAJ&hl=en), > [Manushree Vasu](https://in.linkedin.com/in/v-manushree), > [Shiji Song](https://scholar.google.com/citations?user=rw6vWdcAAAAJ&hl=en&oi=ao), > [Gao Huang](https://www.gaohuang.net), > [Humphrey Shi](https://www.humphreyshi.com) https://github.com/JiayiGuo821/Smooth-Diffusion-Dev/assets/53193040/f965242f-968e-4e62-845c-dd3374a70fcf <p align="center"> <strong>Smooth Diffusion</strong> is a new category of diffusion models that is simultaneously high-performing and smooth. </p> <p align="center"> <img src="assets/repo_figures/Picture1.jpg" width="1080px"/> Our method formally introduces latent space smoothness to diffusion models like Stable Diffusion. This smoothness dramatically aids in: 1) improving the continuity of transitions in image interpolation, 2) reducing approximation errors in image inversion, and 3) better preserving unedited contents in image editing. </p> ## News - [2024.09.24] Since SD 1.5 is currently unavailable, we set Realistic_Vision_V2.0 as our default model. - [2024.03.25] Our demo is available on 🤗 [Huggingface Space](https://huggingface.co/spaces/shi-labs/Smooth-Diffusion)! - [2024.03.20] Code, model, and demo released! - [2024.02.27] Smooth Diffusion is accepted by CVPR 2024! - [2023.12.08] Paper released! ## ToDo - ☑️ Release code and model weights - ☑️ Gradio Demo ## Overview <p align="center"> <img src="assets/repo_figures/Picture2.jpg" width="1080px"/> <strong>Smooth Diffusion</strong> (c) enforces the ratio between the variation of the input latent and the variation of the output prediction is a constant. We propose <strong>Training-time Smooth Diffusion</strong> (d) to optimize a "single-step snapshot" of the variation constraint in (c). DM: Diffusion model. Please refer to our paper for additional details. </p> ## Code ### Setup ``` conda create --name smooth-diffusion python=3.9 conda activate smooth-diffusion pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 pip install -r requirements.txt ``` ### Inference (Gradio Demo) We provide a WebUI empowered by [Gradio](https://github.com/gradio-app/gradio). Start the WebUI with the following command: ``` python app.py ``` ### Training We provide scripts for data downloading and training. Unfortunately, the LAION dataset is currently unavailable due to safety review. [[Offcial note by LAIOM.ai](https://laion.ai/notes/laion-maintanence/)] (Update: LAION is available now. Have fun!) ``` # Download LAION aesthetics 6.5+ python download_regularization_images.py # Train smooth LoRA bash train.sh ``` ## Visualizations ### Image Interpolation > Using the Smooth LoRA trained atop Stable Diffusion V1.5. <p align="center"> <img src="assets/repo_figures/Picture3.jpg" width="1080px"/> </p> > Integrating the above Smooth LoRA into other community models. <p align="center"> <img src="assets/repo_figures/Picture4.jpg" width="1080px"/> </p> ### Image Inversion <p align="center"> <img src="assets/repo_figures/Picture5.jpg" width="1080px"/> </p> ### Image Editing <p align="center"> <img src="assets/repo_figures/Picture6.j
Excerpt of 4,786 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f84c38b34343c64f, llm:Repository title/description: 'Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024' — indicates research and code for diffusion models and latent space smoothing (image generation).
matched fp:f84c38b34343c64f, llm:Repository title/description: 'Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024' — indicates research and code for diffusion models and latent space smoothing (image generation).
matched fp:f84c38b34343c64f, llm:Repository title/description: 'Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024' — indicates research and code for diffusion models and latent space smoothing (image generation).