Research map / Image generation / Text-to-image diffusion
DreamArtist: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter
Ziyi Dong, Pengxu Wei, Liang Lin
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 positive-negative adapters to prompt tuning (ablation) | DreamArtist · LAION-2B natural images | Style loss: 2.46 -> 1.29 | Improved |
| add positive-negative adapters to prompt tuning (ablation) | DreamArtist · LAION-2B natural images | LPIPS: 0.62 -> 0.46 | Improved |
| add positive-negative adapters to prompt tuning (ablation) | DreamArtist · Danbooru anime | Style loss: 0.69 -> 0.38 | Improved |
| add positive-negative adapters to prompt tuning (ablation) | DreamArtist · Danbooru anime | CFV: 1.28 -> 1.03 | Hurt |
| add positive-negative adapters to prompt tuning (ablation) | DreamArtist · LAION-2B natural images | CAS: 0.83 -> 0.89 | Improved |
| add reconstruction loss L_rec (gamma=3) (ablation) | DreamArtist · reconstruction loss ablation | CDS: 0.68 -> 0.72 | Mixed |
| add reconstruction loss L_rec (gamma=3) (ablation) | DreamArtist · reconstruction loss ablation | LPIPS: 0.629 -> 0.613 | Improved |
| increase negative guidance gamma from 3 to 5 (ablation) | DreamArtist · gamma sweep | CAS: 0.79 -> 0.87 | Mixed |
| increase gamma from 3 to 7 (ablation) | DreamArtist · gamma sweep | CAS: 0.79 -> 0.92 | Mixed |
| use DreamArtist instead of TI in human Turing test | DreamArtist · Human evaluation (700 participants) | failure rate: 26.6% -> 34.5% | Improved |
| positive embedding length beyond 3 (ablation) | DreamArtist · embedding length analysis | qualitative | Hurt |
Closest papers by meaning
- Rich Human Feedback for Text-to-Image Generation (CVPR 2024 · similarity 0.87)
- DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation (ICLR 2025 · similarity 0.87)
- Diffusion Self-Distillation for Zero-Shot Customized Image Generation (CVPR 2025 · similarity 0.87)
- Enhancing Creative Generation on Stable Diffusion-based Models (CVPR 2025 · similarity 0.86)
- Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models (AAAI 2025 · similarity 0.86)
- OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance (NeurIPS 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.
