Research map / Image generation / Text-to-image diffusion
HybridBooth: Hybrid Prompt Inversion for Efficient Subject-Driven Generation
Shanyan Guan, Yanhao Ge, Ying Tai, Jian Yang, Wei Li, Mingyu You
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 |
|---|---|---|---|
| add the word embedding probe stage before refinement (ablation) | HybridBooth · CelebA-HQ | DINO-I: 0.068 -> 0.644 | Improved |
| add the residual refinement stage after the probe (ablation) | HybridBooth · CelebA-HQ | DINO-I: 0.568 -> 0.644 | Improved |
| add DINOv2 features alongside CLIP features (ablation) | HybridBooth · CelebA-HQ | DINO-I: 0.453 -> 0.644 | Improved |
| add CLIP features alongside DINO features (ablation) | HybridBooth · CelebA-HQ | DINO-I: 0.510 -> 0.644 | Improved |
| add mask regularization loss on cross-attention (ablation) | HybridBooth · CelebA-HQ | CLIP-T: 0.203 -> 0.246 | Improved |
| add mask regularization loss on cross-attention (ablation) | HybridBooth · CelebA-HQ | DINO-I: 0.625 -> 0.644 | Improved |
| increase number of estimated word embeddings (ablation) | HybridBooth · CelebA-HQ | prompt and subject fidelity | Improved |
| use HybridBooth instead of FastComposer | subject-driven generation · CelebA-HQ | CLIP-I: 0.782 -> 0.865 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FastComposer — FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention (IJCV 2024) · better on 2 of 2 shared results
- ELITE — ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation (ICCV 2023) · better on 1 of 1 shared result
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
- Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models (CVPR 2024 · similarity 0.89)
- AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation (NeurIPS 2024 · similarity 0.88)
- AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models (NeurIPS 2024 · similarity 0.88)
- On Discrete Prompt Optimization for Diffusion Models (ICML 2024 · similarity 0.87)
- Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models (ICLR 2025 · similarity 0.87)
- Decoupled Textual Embeddings for Customized Image Generation (AAAI 2024 · similarity 0.87)
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.
