Text Slider uses LoRA adapters on pre-trained text encoders to identify low-rank directions for efficient, plug-and-play continuous concept control in diffusion-based image and video synthesis.
Understanding the latent space of diffusion models through the lens of riemannian geometry
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters
Text Slider uses LoRA adapters on pre-trained text encoders to identify low-rank directions for efficient, plug-and-play continuous concept control in diffusion-based image and video synthesis.