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.
Paint by Example: Exemplar-based Image Editing with Diffusion Models
| Date | Stars |
|---|---|
| 2026-07-24 | 1253 |
| 2026-07-25 | 1253 |
| 2026-07-28 | 1254 |
| 2026-07-30 | 1254 |
| 2026-07-31 | 1254 |
| 2026-08-06 | 1254 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Paint by Example: Exemplar-based Image Editing with Diffusion Models  ### [Paper](https://arxiv.org/abs/2211.13227) | [Huggingface Demo](https://huggingface.co/spaces/Fantasy-Studio/Paint-by-Example) <!-- <br> --> [Binxin Yang](https://orcid.org/0000-0003-4110-1986), [Shuyang Gu](http://home.ustc.edu.cn/~gsy777/), [Bo Zhang](https://bo-zhang.me/), [Ting Zhang](https://www.microsoft.com/en-us/research/people/tinzhan/), [Xuejin Chen](http://staff.ustc.edu.cn/~xjchen99/), [Xiaoyan Sun](http://staff.ustc.edu.cn/~xysun720/), [Dong Chen](https://www.microsoft.com/en-us/research/people/doch/) and [Fang Wen](https://www.microsoft.com/en-us/research/people/fangwen/). <!-- <br> --> ## Abstract >Language-guided image editing has achieved great success recently. In this paper, for the first time, we investigate exemplar-guided image editing for more precise control. We achieve this goal by leveraging self-supervised training to disentangle and re-organize the source image and the exemplar. However, the naive approach will cause obvious fusing artifacts. We carefully analyze it and propose an information bottleneck and strong augmentations to avoid the trivial solution of directly copying and pasting the exemplar image. Meanwhile, to ensure the controllability of the editing process, we design an arbitrary shape mask for the exemplar image and leverage the classifier-free guidance to increase the similarity to the exemplar image. The whole framework involves a single forward of the diffusion model without any iterative optimization. We demonstrate that our method achieves an impressive performance and enables controllable editing on in-the-wild images with high fidelity. > ## News - *2023-11-28* The recent work Asymmetric VQGAN improves the preservation of details in non-masked regions. For comprehensive details, please refer to the associated [paper](https://arxiv.org/abs/2306.04632), [github]( https://github.com/buxiangzhiren/Asymmetric_VQGAN). - *2023-05-13* Release code for quantitative results. - *2023-03-03* Release test benchmark. - *2023-02-23* Non-official 3rd party apps support by [ModelScope](https://www.modelscope.cn/models/damo/cv_stable-diffusion_paint-by-example/summary) (the largest Model Community in Chinese). - *2022-12-07* Release a [Gradio](https://gradio.app/) demo on [Hugging Face](https://huggingface.co/spaces/Fantasy-Studio/Paint-by-Example) Spaces. - *2022-11-29* Upload code. ## Requirements A suitable [conda](https://conda.io/) environment named `Paint-by-Example` can be created and activated with: ``` conda env create -f environment.yaml conda activate Paint-by-Example ``` ## Pretrained Model We provide the checkpoint ([Google Drive](https://drive.google.com/file/d/15QzaTWsvZonJcXsNv-ilMRCYaQLhzR_i/view?usp=share_link) | [Hugging Face](https://huggingface.co/Fantasy-Studio/Paint-by-Example/resolve/main/model.ckpt)) that is trained on [Open-Images](https://storage.googleapis.com/openimages/web/index.html) for 40 epochs. By default, we assume that the pretrained model is downloaded and saved to the directory `checkpoints`. ## Testing To sample from our model, you can use `scripts/inference.py`. For example, ``` python scripts/inference.py \ --plms --outdir results \ --config configs/v1.yaml \ --ckpt checkpoints/model.ckpt \ --image_path examples/image/example_1.png \ --mask_path examples/mask/example_1.png \ --reference_path examples/reference/example_1.jpg \ --seed 321 \ --scale 5 ``` or simply run: ``` sh test.sh ``` Visualization of inputs and output:    ## Training ### Data preparing - Download separate packed files of Open-Images dataset from [CVDF's site](https://github.com/cvdfoundation/open-images-dataset#download-images-with-bounding-boxes-annotations) and unzip them to the directory `dataset/open-images/images`. - Download bbox annotations of Open-Images dataset from [Open-Images official site
Excerpt of 8,779 characters
Read on GitHub
64
2
Bo Zhang · Microsoft · China
2
1
1
1
Ikko Eltociear Ashimine · Japan
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b446f341abf36b4f, topic:stable-diffusion, topic:diffusion-models, topic:image-generation
matched fp:b446f341abf36b4f, topic:deep-learning, topic:pytorch