Research map / Image generation / Text-to-image diffusion
Paint Anything: Toward Any-Color Controllable Image Generation and Editing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an any-color controllable image generation and editing approach that lets users specify objects by arbitrary 24-bit hex color values.
Problem
Precise any-color control (arbitrary 24-bit hex values) for image generation and editing, beyond coarse color words that prior color generation, editing, and colorization methods handle.
Approach
Targets exact hex-specified object colors rather than coarse color words; the abstract notes prior methods rely on task-specific modules or training, which this work aims to avoid. Specific mechanism not stated in the abstract.
Closest papers by meaning
- Automatic Controllable Colorization via Imagination (CVPR 2024 · similarity 0.88)
- Color Conditional Generation with Sliced Wasserstein Guidance (NeurIPS 2025 · similarity 0.86)
- MangaNinja: Line Art Colorization with Precise Reference Following (CVPR 2025 · similarity 0.85)
- Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis (CVPR 2024 · similarity 0.85)
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025 · similarity 0.85)
- Free-Lunch Color-Texture Disentanglement for Stylized Image Generation (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.