wow.. ChatGPT just dropped Image Editor you can now select an area of the image to add, remove or change things, its only available to some users now here's how to get access and some tricks:

✨Hi3DGen now runs locally via ComfyUI! 🏠GPT-4o/Gemini + Hi3DGen = Your dream home in minutes! Get started: github.com/Stable-X/Comfy…

🚀🚀🚀Introducing VideoScene (CVPR'25) - a turbo upgrade of ReconX! Our one-step video diffusion model bridges the gap from video to 3D, outpacing slow multi-step pipelines. Paper: arxiv.org/abs/2504.01956 Project Page: hanyang-21.github.io/VideoScene Code: github.com/hanyang-21/Vid…

Thanks AK for sharing our work on CVPR 2025, #CVPR for one-step 3D consistent video generation that bridges the gap from video to 3D! Paper: arxiv.org/abs/2504.01956 Project Page: hanyang-21.github.io/VideoScene GitHub: github.com/hanyang-21/Vid… #VIDEO #aigc

Pusa is out on Hugging Face Thousands Timesteps Video Diffusion Model A ​​single model​​ that unlocks: • Text-to-Video​​ • Image-to-Video​​ ​​ • Start/End Frames to Video • Video Transitions • Video Extensions​​ • Next-frame prediction​​ ​​ • Novel sampling

Video Game Bench introduce a research preview of VideoGameBench, a benchmark which challenges vision-language models to complete, in real-time, a suite of 20 different popular video games from both hand-held consoles and PC GPT-4o, Claude Sonnet 3.7, Gemini 2.5 Pro, and Gemini

Great Talk！

Gemini + Imagen + Veo = ✨ cinematic magic ✨ At #GoogleCloudNext, we used Gemini, Imagen and Veo on Vertex AI to build this simple video creation experience. Check it out ⬇️

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Elevate Visual-Spatial Intelligence with Spatial-MLLM! 🚀🚀🚀 Discover how we incorporate 3D information to help MLLMs better think in space in our work: Spatial-MLLM. 🔗Code: github.com/diankun-wu/Spa… 🌐Project Page: diankun-wu.github.io/Spatial-MLLM/ 📄Paper: arxiv.org/abs/2505.23747

Big thanks to AK for sharing our work! We're thrilled to announce Spatial-MLLM, our latest work to improve spatial reasoning in multimodal large language models. The model code is open-sourced!🎉 Code: github.com/diankun-wu/Spa… Project page: diankun-wu.github.io/Spatial-MLLM/

🚀UniWorld: a unified model that skips VAEs and uses semantic features from SigLIP! Using just 1% of BAGEL’s data, it outperforms on image editing and excels in understanding & generation. 🌟Now data, model, training & evaluation script are open-source! github.com/PKU-YuanGroup/…

⚡️⚡️⚡️Introducing 4D-Fly (CVPR'25) - for fast reconstructing 4D scenes from monocular videos in minutes. Compared to previous methods, our approach achieves a 20x speed-up while maintaining comparable or superior reconstruction quality. Project page: diankun-wu.github.io/4D-Fly/ #4D

Video-T1 has been accepted to #ICCV2025. See you all in Hawaii !🌴

DimensionX has been accepted to #ICCV2025. See you all in Hawaii !🌴

🚀 Unveiling Unify Model and Spatial Intelligence at #ICCV2025 in our LangScene-X! Unify 3D scene reconstruction, generation, and understanding in one video diffusion model! Code is open sourced at github.com/liuff19/LangSc…

Big thanks to AK for sharing LangScene-X, our latest work to unify 3D scene reconstruction, generation, and understanding in a single video diffusion! The model code is open-sourced!🎉 Code: github.com/liuff19/LangSc… Project page: liuff19.github.io/LangScene-X/