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.
Open-Set Grounded Text-to-Image Generation
| Date | Stars |
|---|---|
| 2026-07-31 | 2227 |
| 2026-08-02 | 2227 |
| 2026-08-06 | 2227 |
| 2026-08-12 | 2227 |
| 2026-08-18 | 2224 |
| 2026-08-21 | 2223 |
| 2026-08-27 | 2223 |
| 2026-08-28 | 2224 |
| 2026-08-31 | 2223 |
| 2026-09-04 | 2222 |
| 2026-09-10 | 2223 |
| 2026-09-11 | 2224 |
| 2026-09-19 | 2225 |
| 2026-09-20 | 2225 |
Today
— stars today
This week
+1 stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.04%/day
# GLIGEN: Open-Set Grounded Text-to-Image Generation (CVPR 2023) [Yuheng Li](https://yuheng-li.github.io/), [Haotian Liu](https://hliu.cc), [Qingyang Wu](https://scholar.google.ca/citations?user=HDiw-TsAAAAJ&hl=en/), [Fangzhou Mu](https://pages.cs.wisc.edu/~fmu/), [Jianwei Yang](https://jwyang.github.io/), [Jianfeng Gao](https://www.microsoft.com/en-us/research/people/jfgao/), [Chunyuan Li*](https://chunyuan.li/), [Yong Jae Lee*](https://pages.cs.wisc.edu/~yongjaelee/) (*Co-senior authors) [[Project Page](https://gligen.github.io/)] [[Paper](https://arxiv.org/abs/2301.07093)] [[Demo](https://huggingface.co/spaces/gligen/demo)] [[YouTube Video](https://youtu.be/-MCkU7IAGKs)]  [](https://youtu.be/-MCkU7IAGKs) - Go beyond text prompt with GLIGEN: enable new capabilities on frozen text-to-image generation models to ground on various prompts, including box, keypoints and images. - GLIGEN’s zero-shot performance on COCO and LVIS outperforms that of existing supervised layout-to-image baselines by a large margin. ## :fire: News * **[2023.11.2]** GLIGEN is integreated into [LLaVA-Interactive](https://llava-vl.github.io/llava-interactive/): an all-in-one demo for Image Chat, Segmentation, Generation and Editing. Experience the future of interactive image editing with visual chat. [[Project Page](https://llava-vl.github.io/llava-interactive/)] [[Demo](https://6dd3-20-163-117-69.ngrok-free.app/)] [[Code](https://github.com/LLaVA-VL/LLaVA-Interactive-Demo)] [[Paper](https://arxiv.org/abs/2311.00571)] <center> <img src="https://github.com/LLaVA-VL/llava-interactive/blob/main/images/llava_interactive_workflow.png" width="30%"> </center> * **[2023.04.18]** We have updated our arxiv paper. We explain the difference between GLIGEN and ControlNet [here](docs/gligen_vs_controlnet.MD) to help researchers to have a better and deeper understanding. * **[2023.04.08]** GLIGEN is combined with [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO), which free humans from anotating bounding boxes and their concepts. Given a language prompt, Grounding DINO localizes the concepts with boxes: image $\rightarrow$ (box, concept), then GLIGEN inpaint the image: (box, concept) $\rightarrow$ image: <center> <img src="https://camo.githubusercontent.com/4dabf8128cd4f40eaa97ee45d050ddcd8063356f631d98072fb5a5c19c35fa9c/68747470733a2f2f68756767696e67666163652e636f2f5368696c6f6e674c69752f47726f756e64696e6744494e4f2f7265736f6c76652f6d61696e2f47445f474c4947454e2e706e67" width="600"> </center> * **[2023.03.22]** [Our fork on diffusers](https://github.com/gligen/diffusers/tree/gligen/examples/gligen) with support of text-box-conditioned generation and inpainting is released. It is now faster, more flexible, and automatically downloads and loads model from Huggingface Hub! Try it out! * **[2023.03.20]** Stay up-to-date on the line of research on *grounded image generation* such as GLIGEN, by checking out [`Computer Vision in the Wild (CVinW) Reading List`](https://github.com/Computer-Vision-in-the-Wild/CVinW_Readings#orange_book-grounded-image-generation-in-the-wild). * **[2023.03.19]** GLIGEN is covered by great Yannic Kilcher in his latest YouTube video on [`The biggest week in AI`](https://www.youtube.com/watch?v=YqPYDWPYXFs&t=2245s). * **[2023.03.05]** Gradio demo code is released at [`GLIGEN/demo`](https://github.com/gligen/GLIGEN/tree/master/demo). * **[2023.03.03]** Code base and checkpoints are released. * **[2023.02.28]** Paper is accepted to CVPR 2023. * **[2023.01.17]** GLIGEN paper and demo is released. ## Requirements We provide [dockerfile](env_docker/Dockerfile) to setup environment. ## Download GLIGEN models We provide ten checkpoints for different use scenarios. All models here are based on SD-V-1.4. | Mode | Modality | Download
Excerpt of 11,524 characters
Read on GitHub
21
Haotian Liu · xAI · United States
16
11
Piotr Migdał · ex: Quantum Flytrap CTO & cofounder · Poland
6
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a3190cc01ba3503d, desc:text-to-image, desc:image generation