Research map / Image generation / Text-to-image diffusion
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
Zeju Qiu, Weiyang Liu, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, Bernhard Schölkopf
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 |
|---|---|---|---|
| use OFT instead of DreamBooth/LoRA finetuning | Stable Diffusion v1.5 · DreamBooth subject-driven generation | DINO: 0.614 -> 0.632 | Improved |
| use OFT instead of DreamBooth | Stable Diffusion v1.5 · DreamBooth subject-driven generation | CLIP-T: 0.239 -> 0.237 | No clear effect |
| use OFT instead of ControlNet | Stable Diffusion v1.5 · Segmentation to image (ADE20K) | mIoU: 20.88 -> 27.06 | Improved |
| add the orthogonal constraint (ablation) | OFT · Controllable generation (ControlNet setting) | qualitative control | Improved |
| add the epsilon deviation constraint (COFT vs OFT) (ablation) | OFT · Subject-driven generation, long training | stability | Improved |
| COFT vs OFT | Stable Diffusion v1.5 · Landmark to face | landmark error: 7.07 -> 6.92 | Improved |
| increase number of diagonal blocks from 4 to 16 (ablation) | OFT · Segmentation to image (ADE20K) | mIoU: 27.06 -> 21.0 | Hurt |
| decrease number of diagonal blocks from 4 to 2 (ablation) | OFT · Segmentation to image (ADE20K) | mIoU: 27.06 -> 27.18 | Mixed |
| add post-stage magnitude fitting (re-scaled) (ablation) | COFT · ADE20K S2I | FID: 30.8 -> 30.2 | Improved |
| finetune only conv layers instead of attention layers (ablation) | COFT · ADE20K S2I | FID: 30.8 -> 39.8 | Hurt |
| finetune attention plus conv layers (ablation) | COFT · ADE20K S2I | FID: 30.8 -> 30.4 | Improved |
Closest papers by meaning
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation (ICLR 2024 · similarity 0.89)
- OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance (NeurIPS 2024 · similarity 0.87)
- Progressive Text-to-Image Diffusion with Soft Latent Direction (AAAI 2024 · similarity 0.87)
- On Discrete Prompt Optimization for Diffusion Models (ICML 2024 · similarity 0.87)
- Simplifying Control Mechanism in Text-to-Image Diffusion Models (AAAI 2025 · similarity 0.87)
- SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation (CVPR 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.
