- New work from MiniMax Visual Tokenizer Pre-training (VTP) 🔥 a framework that helps visual tokenizers learn better representations for diffusion-based image generation. huggingface.co/collections/...
Dec 16, 2025 11:17
- ✨ Understanding matters more than reconstruction ✨ Makes visual tokenizers scalable ✨ Same DiT training > much better image quality ✨ +65.8% better FID and 3× faster training
