Dongliang Chang

@dasayan05 hahahahaha

can we ?

Huge congratulations to PAI and CVSSP colleagues whose papers have been accepted for the Conference on Computer Vision and Pattern Recognition #CVPR2024 🤩 See their papers here 👉tinyurl.com/3mywnfk2

🌕

🐦🦆🦅🦉Excited to share #DreamCreature, which creates novel creatures by learning *1000+* fine-grained sub-concepts. 🚨Code & Gradio demo on Colab is available now!! ⌨️GitHub: github.com/kamwoh/dreamcr… 📜paper: huggingface.co/papers/2311.15…

🤫

We are feeling very festive today! For campus opening hours over the winter break, visit: my.surrey.ac.uk/news/winter-br…

⛄️⛄️❄️❄️

@krishnanrohit @ysu_nlp To create new animals that do not exist, we proposed a solution called DreamCreature, which learns to "draw" the parts of the animal (in our paper, we show bird & dog only) with SD and recombine them to create new animals. twitter.com/kam_woh/status…

University of Surrey introduces DemoFusion, a game-changing AI tool, democratising high-res image creation without costly subscriptions or powerful computers. tech.hindustantimes.com/amp/tech/news/…

Fully funded PhD studentships for outstanding Chinese students at CVSSP&PAI, UK: surrey.ac.uk/fees-and-fundi…. Start date: 1 October 2024 Duration: 4 years Application deadline: 12 January 2024 About CVSSP: surrey.ac.uk/centre-vision-… About PAI: surrey.ac.uk/artificial-int…

🎉 Exciting News from Our Team! 🌟 We're thrilled to announce a major milestone for our open-source project, DemoFusion: We've just surpassed 1,000 stars on GitHub! 🚀 Check out the project here: github.com/PRIS-CV/DemoFu… #DemoFusion #OpenSource #SketchX

Pretty interesting "upscaling" results with DemoFusion. Started with 1024x1024, and ended up at 3072x3072. I'll drop samples in the thread to show how each image turned out + the repo at the end to check out. Here is the starting image 🧵

DemoFusion is a new tool made by the University of Surrey that promises to bring low-cost, high-resolution artificial intelligence (AI) image generation to a wider audience without the need for powerf… subject.news/article/149401 #ai #image #demofusion #high-resolution #powerful

🔗 x.com/i/status/17330… DemoFusion：无需 $$$ 即可实现高分辨率图像生成的民主化 🖼 Img2Img Colab 🥳感谢 @RuoyiDu ❤ @DL_Chang ❤ @tmh31 ❤ @yizhe_song ❤ Zhanyu Ma ❤ 🌐页面：ruoyidu.github.io/demofusion/dem… 📄论文：arxiv.org/abs/2311.16973 🧬代码：github.com/PRIS-CV/DemoFu… 🦒colab 由 modelslab.com 提供：请尝试 🐣 github.com/camenduru/Demo…

正巧昨晚 @0xstory_xhu 也和我聊到这个，实测后我发现有些摄影场景一点也不比 @Magnific_AI 差，真是尴尬。我主观上感觉 Magnific 在动漫场景的细节上更细腻，明天我发发测试图。大家可以看看小互的详细介绍先。相比较于 Magnific 昂贵的价格，DemoFusion 还是免费的…

DemoFusion: Democratizing the Generation of High-Resolution Images 🌟 We have seen image enhancement tools (upscaling) with high prices, but now DemoFusion arrives, changing the game. This innovative tool is democratizing the generation of high-resolution images, making it accessible to everyone, and best of all, it's free! Today, we will explore how DemoFusion is opening up a new world of possibilities in digital art and creativity. Thanks for research @ruoyidu's and also thanks to @radamar for sharing 🫶🏻 Have you already experimented with DemoFusion? x.com/radamar/status…

@annabella23521 Thanks! I use opensource diffusion models to generate pics generally for fun purposes - the above one is generated using opensource demofusion - github.com/PRIS-CV/DemoFu…

清华大学新发布的DemoFusion这个模型简直是太棒了！！ --人性化：主打民主化高分辨率图像生成，完全免费！ --超高分辨率放大：可将SDXL生成的1024×1024分辨率图像，提升至4倍、16倍，甚至更高！ --低内存资源，开箱即用：DemoFusion设计得既高效又易于使用，不需要大量的内存资源或复杂的调整过程！

demofusion xl

尝试了一下DemoFusion这个图片放大项目，这玩意的资源消耗真是恐怖，2048*2048的图片A100居然跑了两分半的时间。 前两张是动漫图片，后两张是写实照片，不过效果确实好。可能是实现问题部分细节有一些崩坏的纹理。 动漫的图片会被识别成写实的照片，可能是提示词问题。 原图放在下面的推里面了可以对比一下生成前后的效果。 想体验的可以用这个Colab链接尝试，不过不是Pro的就算了，T4得跑好久：colab.research.google.com/github/camendu…