TokenVerse

TokenVerse is a method for multi-concept personalization that uses a pre-trained text-to-image diffusion model. It can disentangle complex visual elements and attributes from a single image and combine concepts extracted from multiple images, supporting objects, accessories, materials, pose and lighting. It uses a DiT-based text-to-image model and learns modulation-space directions for each word.

Website Directory import
0 shouts Added Sep 23, 2026 token-verse.github.io
token-verse.github.io/
TokenVerse website preview

Features

Links

Tags