ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
One diffusion to generate them all
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TICoE achieves more precise and faithful concept erasure in text-to-image models by collaborating text and image data through a convex manifold and hierarchical learning, outperforming prior methods.
citing papers explorer
-
ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
-
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
TICoE achieves more precise and faithful concept erasure in text-to-image models by collaborating text and image data through a convex manifold and hierarchical learning, outperforming prior methods.