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.
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
| Date | Stars |
|---|---|
| 2026-07-24 | 4998 |
| 2026-07-25 | 4999 |
| 2026-07-28 | 4999 |
| 2026-07-30 | 4999 |
| 2026-08-06 | 4999 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Tiled Diffusion & VAE extension for sd-webui [![CC BY-NC-SA 4.0][cc-by-nc-sa-shield]][cc-by-nc-sa] This extension is licensed under [CC BY-NC-SA](https://creativecommons.org/licenses/by-nc-sa/4.0/), everyone is FREE of charge to access, use, modify and redistribute with the same license. **You cannot use versions after AOE 2023.3.28 for commercial sales (only refers to code of this repo, the derived artworks are NOT restricted).** 由于部分无良商家销售WebUI，捆绑本插件做卖点收取智商税，本仓库的许可证已修改为 [CC BY-NC-SA](https://creativecommons.org/licenses/by-nc-sa/4.0/)，任何人都可以自由获取、使用、修改、以相同协议重分发本插件。 **自许可证修改之日(AOE 2023.3.28)起，之后的版本禁止用于商业贩售 (不可贩售本仓库代码，但衍生的艺术创作内容物不受此限制)。** If you like the project, please give me a star! ⭐ [](https://ko-fi.com/pkuliyi2015) **** The extension helps you to **generate or upscale large images (≥2K) with limited VRAM (≤6GB)** via the following techniques: - Reproduced SOTA Tiled Diffusion methods - [Mixture of Diffusers](https://github.com/albarji/mixture-of-diffusers) - [MultiDiffusion](https://multidiffusion.github.io) - [Demofusion](https://github.com/PRIS-CV/DemoFusion) - Our original Tiled VAE method - My original Tiled Noise Inversion method ### Features - Core - [x] [Tiled VAE](#tiled-vae) - [x] [Tiled Diffusion: txt2img generation for ultra-large image](#tiled-diff-txt2img) - [x] [Tiled Diffusion: img2img upscaling for image detail enhancement](#tiled-diff-img2img) - [x] [Regional Prompt Control](#region-prompt-control) - [x] [Tiled Noise Inversion](#tiled-noise-inversion) - Advanced - [x] [ControlNet support]() - [x] [StableSR support](https://github.com/pkuliyi2015/sd-webui-stablesr) - [x] [SDXL support](experimental) - [x] [Demofusion support]() 👉 在 [wiki](https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111/wiki) 页面查看详细的文档和样例，以及由 [@PotatoBananaApple](https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111/discussions/120) 制作的 [快速入门教程](https://civitai.com/models/34726) 👉 Find detailed documentation & examples at our [wiki](https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111/wiki), and quickstart [Tutorial](https://civitai.com/models/34726) by [@PotatoBananaApple](https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111/discussions/120) 🎉 ### Examples ⚪ Txt2img: generating ultra-large images `prompt: masterpiece, best quality, highres, city skyline, night.`  ⚪ Img2img: upcaling for detail enhancement | original | x4 upscale | | :-: | :-: | |  |  | ⚪ Regional Prompt Control | region setting | output1 | output2 | | :-: | :-: | :-: | |  |  |  | |  |  |  | ⚪ ControlNet support | original | with canny | | :-: | :-: | |  |  | | 重绘 “清明上河图” | | :-: | :-: | | original | 
185
45
17
Kohaku-Blueleaf · NTHU · Taiwan
2
Andray
2
Vladimir Mandic · Croatia
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9966fe19c604c72b, topic:stable-diffusion, topic:image-generation, readme:upscaling