做文生图研究的团队终于有了一个大规模、去重、重新标注的开源数据集，可以直接用于训练和复现实验，建议点开看看数据集和代码库。
Jasper AI 发布了 MONET 数据集，包含 1.05 亿个经过去重和重新标注的图像-文本对，采用 Apache 2.0 开源许可，是目前最大的开放许可文生图数据集之一。该数据集托管在 Hugging Face 上，旨在推动可复现的文生图研究。同时，Jasper 还开源了 Nano T2I 代码库，帮助开发者训练自己的文生图模型。这一发布解决了开源文生图领域缺乏大规模、高质量、可复现数据集的问题。
With 104M of image-text pairs, this is one of the largest, if not the largest, openly-licensed image...
With 104M of image-text pairs, this is one of the largest, if not the largest, openly-licensed image dataset And it's on @huggingface !! Kudos @heyjasperai Clément Chadebec @CChadebec 📢 New @heyjasper release ! 📢 MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research. Nano T2I 🖌️ : A codebase to train your own T2I model 🤗 @huggingf huggingface.co/datasets/jaspe… QIaF github.com/gojasper/nano-… U2wjtW Very excited about this new release, pushing the boundaries of open and reproducible T2I research. Congrats to the team! Benjamin Aubin Gonzalo Quintana @onurxtasar @UlaLaParis @_jeev2 @dh7net @clipdropapp @heyjasperai Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 3 🔄 3 ❤️ 13 👀 2222 📊 5 ⚡