In recent months, numerous AIGC 3D generation algorithms have emerged, and the latest release, DreamGaussian, makes me feel that 3D generation has nearly reached the stable diffusion moment of 2D generation—challenging the "quality, speed, and generalization" triangle of impossibility!
I finally found some time to start watching the new series of short LLM courses by Andrew Ng. To keep myself motivated and on track with my learning, I will be sharing my study notes over this period, aiming to make progress together with everyone! 🤗
This is the only non-technical article I've written this year, yet it’s the most important one, as it addresses the most crucial question in the age of AI: how to maintain self-coherence.
Try creating an animation of silicon-based lifeforms using a combination of artificial evolution guidance, GPT-4/ChatGLM, Stable Diffusion/Midjourney, and Runway GEN2. It feels like we can create worlds from scratch with AI!
The issues surrounding 3D generation are nearing resolution, but the reasonable placement and distribution of generated 3D objects have now become a new challenge.
