Research map / Image generation / Text-to-image diffusion
MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models
Jing Zhao, Heliang Zheng, Chaoyue Wang, Long Lan, Wenjing Yang
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 |
|---|---|---|---|
| blend noises with saliency-aware mask instead of weighted-sum averaging of two models' noises (ablation) | SNB (Stable Diffusion + expert model) · fusion applications (qualitative) | content fidelity | Improved |
| use saliency-aware mask instead of annotated mask (Blended-Diffusion style) (ablation) | SNB general + car model · car in snowy forest (qualitative) | detail preservation | Improved |
| fuse general model with DreamBooth model via SNB instead of DreamBooth alone | DreamBooth · recontextualization (qualitative) | subject presence and detail | Improved |
| fuse general model with fine-grained or cartoon expert via SNB instead of general model alone | Stable Diffusion v1-4 · fine-grained and cross-domain fusion (qualitative) | object completeness | Improved |
Closest papers by meaning
- DISCO: DISCrete nOise for Conditional Control in Text-to-Image Diffusion Models (NeurIPS 2025 · similarity 0.89)
- InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization (CVPR 2024 · similarity 0.89)
- Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance (CVPR 2024 · similarity 0.88)
- Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models (NeurIPS 2025 · similarity 0.88)
- Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion (CVPR 2025 · similarity 0.88)
- Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models (AAAI 2025 · similarity 0.88)
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.
