view post Post 2737 ๐จ New VQA + captioning dataset! moondream/megalith-mdqaImages from Megalith, captioned using Moondream, then transformed to short-form QA.9M+ images, 6-10 QA pairs per image. See translation ๐ฅ 7 7 ๐ง 1 1 โ 1 1 ๐ 1 1 + Reply
SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images Paper โข 2501.04689 โข Published Jan 8 โข 17
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos Paper โข 2501.04001 โข Published Jan 7 โข 44
Structured 3D Latents for Scalable and Versatile 3D Generation Paper โข 2412.01506 โข Published Dec 2, 2024 โข 68
view post Post 2810 For those Game Developers out there who wants a tool to generate them 3d assets of different game items. I built something for you ๐ JeffreyXiang/TRELLIS-image-large + Qwen/Qwen2.5-72B-Instruct + Freepik/flux.1-lite-8B-alpha = MohamedRashad/Game-Items-GeneratorHappy building ๐ See translation 1 reply ยท ๐ฅ 8 8 ๐ 5 5 + Reply
view post Post 2015 Hey!โจ If you're using HF access tokens, we just released an overview of the permissions for fine-grained tokens by hovering over the badge on token settings page (org and user) It will show the highest permission you've set for each entity ๐ See translation ๐ 7 7 ๐ฅ 3 3 ๐ค 3 3 + Reply