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.
:zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)
| Date | Stars |
|---|---|
| 2026-07-31 | 1407 |
| 2026-08-03 | 1407 |
| 2026-08-06 | 1407 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> ## [ICLR2024] ⚡InstaFlow! One-Step Stable Diffusion with Rectified Flow [[Paper]](https://arxiv.org/abs/2309.06380) [[Demo in 🤗Hugging Face Space]](https://huggingface.co/spaces/XCLiu/InstaFlow) [[Code and Pre-trained Models](https://github.com/gnobitab/InstaFlow/tree/main/code)][[Colab Notebook](https://colab.research.google.com/drive/1mXvIrkbWFwHcZl0sMNjrR3zGtYlrI6re?usp=sharing)] by *Xingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng, Qiang Liu* </div> ## News - (New) 2024/06/07 Our large-scale Rectified Flow is extended to text-to-3D and image inversion/editing! Check out the amazing work from Xiaofeng Yang et al. ([paper](https://arxiv.org/pdf/2406.03293) and [code](https://github.com/yangxiaofeng/rectified_flow_prior))! - 2024/05/17 Try our new few-step model PeRFlow at [here](https://github.com/magic-research/piecewise-rectified-flow)! - 2023/12/04 We updated the [demo](https://huggingface.co/spaces/XCLiu/InstaFlow) in 🤗Hugging Face Space with InstaFlow+[dreamshaper-7](https://huggingface.co/Lykon/dreamshaper-7). Image quality significantly improves! We also provide the Gradio demo for you to run locally [here](https://github.com/gnobitab/InstaFlow/tree/main/code#local-gradio-interface). - 2023/12/04 One-step InstaFlow is compatible with pre-trained LoRAs! See [here](https://github.com/gnobitab/InstaFlow/tree/main#lora). Code is available [here](https://github.com/gnobitab/InstaFlow/tree/main/code#adding-lora-to-2-rectified-flow-or-instaflow-09b). (We thank individual contributor [Dr. Hanshu Yan](https://hanshuyan.github.io/)) - 2023/12/04 ONNX support is available now! [[ONNX InstaFlow]](https://huggingface.co/TheyCallMeHex/InstaFlow-0.9B-ONNX/tree/main) [[ONNX 2-Rectified Flow]](https://huggingface.co/TheyCallMeHex/2-Rectified-Flow-ONNX) [[ONNXStack UI]](https://github.com/saddam213/OnnxStack/releases/tag/v0.10.0) (We thank [saddam213](https://github.com/saddam213)) - 2023/11/23 Colab notebook is online now. Try it [here](https://colab.research.google.com/drive/1mXvIrkbWFwHcZl0sMNjrR3zGtYlrI6re?usp=sharing). (We thank individual contributor [ xaviviro](https://github.com/xaviviro)) - 2023/11/22 One-step InstaFlow is compatible with pre-trained ControlNets. See [here](https://github.com/gnobitab/InstaFlow/tree/main#controlnet). (We thank individual contributor [Dr. Hanshu Yan](https://hanshuyan.github.io/)) - 2023/11/22 We release the pre-trained models and inference codes [here](https://github.com/gnobitab/InstaFlow/tree/main/code). - 2023/09/26 We provide a demo of InstaFlow-0.9B in 🤗Hugging Face Space. Try it [here](https://huggingface.co/spaces/XCLiu/InstaFlow). ## Introduction Diffusion models have demonstrated remarkable promises in text-to-image generation. However, their efficacy is still largely hindered by computational constraints stemming from the need of iterative numerical solvers at the inference time for solving the diffusion/flow processes. **InstaFlow** is an ```ultra-fast```, ```one-step``` image generator that achieves image quality close to Stable Diffusion, significantly reducing the demand of computational resources. This efficiency is made possible through a recent [Rectified Flow](https://github.com/gnobitab/RectifiedFlow) technique, which trains probability flows with straight trajectories, hence inherently requiring only a single step for fast inference. **InstaFlow** has several advantages: - ```Ultra-Fast Inference```: **InstaFlow** models are **one-step generators**, which directly map noises to images and avoid multi-step sampling of diffusion models. On our machine with A100 GPU, the inference time is around 0.1 second, saving ~90% of the inference time compared to the original Stable Diffusion. - ```High-Quality```: **InstaFlow** generates images with intricate details like Stable Diffusion, and have similar FID on MS COCO 2014 as state-of-the-art text-to-image GANs, like [StyleGAN-T](https://github.com/autonomousvision/stylegan-t). - ```Simple
Excerpt of 9,157 characters
Read on GitHub
XCL · UT Austin · United States
32
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:aec4124eb3b1864c, desc:stable diffusion