Research map / Image generation / Editing and style transfer
AnyFace: Free-Style Text-To-Face Synthesis and Manipulation
Check 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 AnyFace instead of AttnGAN | text-to-face synthesis · Multi-modal CelebA-HQ | FID: 54.22 -> 50.56 | Helped |
| Use AnyFace instead of AttnGAN | text-to-face synthesis · Multi-modal CelebA-HQ | LPIPS: 0.548 -> 0.446 | Helped |
| Use AnyFace instead of AttnGAN | text-to-face synthesis · Multi-modal CelebA-HQ | RFRR: 22.15% -> 29.05% | Helped |
| Use AnyFace instead of AttnGAN | text-to-face synthesis · CelebAText-HQ | FID: 70.47 -> 56.75 | Helped |
| Use AnyFace instead of AttnGAN | text-to-face synthesis · CelebAText-HQ | LPIPS: 0.524 -> 0.431 | Helped |
| Use AnyFace instead of AttnGAN | text-to-face synthesis · CelebAText-HQ | RFRR: 26.54% -> 29.31% | Helped |
| Add diverse triplet loss instead of pairwise loss (ablation) | AnyFace · text-to-face synthesis | facial diversity | Helped |
| Add cross-modal transfer loss (ablation) | AnyFace · Multi-modal CelebA-HQ and CelebAText-HQ | FID | Helped |
| Add cross-modal transfer loss (ablation) | AnyFace · text-to-face synthesis | structured attribute consistency | Helped |
Closest papers by meaning
- Text-Guided 3D Face Synthesis - From Generation to Editing (CVPR 2024 · similarity 0.85)
- AnyText: Multilingual Visual Text Generation and Editing (ICLR 2024 · similarity 0.85)
- Faces that Speak: Jointly Synthesising Talking Face and Speech from Text (CVPR 2024 · similarity 0.85)
- When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation (CVPR 2024 · similarity 0.84)
- Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion (CVPR 2025 · similarity 0.84)
- Controllable 3D Face Generation with Conditional Style Code Diffusion (AAAI 2024 · similarity 0.84)
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.