Research map / Image generation / Editing and style transfer
Inversion-Based Style Transfer With Diffusion Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use attention-based inversion instead of direct textual inversion | InST · CLIP-based evaluation | accuracy (%): 68.84 -> 78.92 | Helped |
| Use attention-based inversion instead of direct textual inversion | InST · CLIP-based evaluation | editability (%): 69.03 -> 80.72 | Helped |
| Add multi-layer attention rather than use MLP (ablation) | InST · CLIP-based evaluation | accuracy (%): 71.03 -> 78.92 | Helped |
| Add multi-layer attention rather than use MLP (ablation) | InST · CLIP-based evaluation | editability (%): 66.99 -> 80.72 | Helped |
| Add dropout in the attention module (ablation) | InST · CLIP-based evaluation | accuracy (%): 72.25 -> 78.92 | Helped |
| Add dropout in the attention module (ablation) | InST · CLIP-based evaluation | editability (%): 66.53 -> 80.72 | Helped |
| Add stochastic inversion to the content image (ablation) | InST · Content preservation during style transfer | content semantics | Helped |
| Increase synthesis Strength (ablation) | InST · Image synthesis | style influence | Helped |
Closest papers by meaning
- ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank (AAAI 2024 · similarity 0.91)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR 2024 · similarity 0.90)
- Z*: Zero-shot Style Transfer via Attention Reweighting (CVPR 2024 · similarity 0.88)
- Music Style Transfer with Time-Varying Inversion of Diffusion Models (AAAI 2024 · similarity 0.87)
- ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation (CVPR 2024 · similarity 0.87)
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models (AAAI 2025 · similarity 0.86)
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.