Research map / Image generation / Editing and style transfer
FontCrafter: High-Fidelity Element-Driven Artistic Font Creation with Visual In-Context Generation
Wuyang Luo, Chengkai Tan, Chang Ge, Binye Hong, Su Yang, Yongjiu Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace CMA with ControlNet for glyph control (ablation) | FontCrafter · Object elements | FID: 193.2 -> 127.5 | Improved |
| replace CMA with T2I-Adapter for glyph control (ablation) | FontCrafter · Object elements | FID: 183.1 -> 127.5 | Improved |
| use visual in-context generation instead of IP-Adapter (ablation) | FontCrafter · Object elements | FID: 213.2 -> 127.5 | Improved |
| use visual in-context generation instead of IP-Adapter (ablation) | FontCrafter · Amorphous elements | User study consistency: 68.4 -> 96.6 | Improved |
| replace CMA with ControlNet (ablation) | FontCrafter · Amorphous elements | Patch FID: 247.9 -> 193.4 | Improved |
| lower attention suppression factor lambda from 1.0 (ablation) | FontCrafter · Qualitative (Fig. 12) | stroke hallucination | Improved |
| add edge repainting post-processing (ablation) | FontCrafter · Qualitative (Fig. 11) | boundary naturalness | Improved |
| FontCrafter vs FontStudio | FontCrafter · Object elements | FID: 205.4 -> 127.5 | Improved |
| FontCrafter vs Anything2Glyph | FontCrafter · Anything2Glyph style set | FID: 297.8 -> 213.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FontStudio — FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation (ECCV 2024) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rethinking Glyph Spatial Information in Font Generation (CVPR 2026 · similarity 0.89)
- VecGlypher: Unified Vector Glyph Generation with Language Models (CVPR 2026 · similarity 0.87)
- VQ-FONT: Few-Shot Font Generation with Structure-Aware Enhancement and Quantization (AAAI 2024 · similarity 0.87)
- FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · similarity 0.87)
- IF-Font: Ideographic Description Sequence-Following Font Generation (NeurIPS 2024 · similarity 0.86)
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · 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.
