TAUE: Training-free Noise Transplant and Cultivation Diffusion Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914401391476736 |
|---|---|
| author | Nagai, Daichi Morita, Ryugo Kitada, Shunsuke Iyatomi, Hitoshi |
| author_facet | Nagai, Daichi Morita, Ryugo Kitada, Shunsuke Iyatomi, Hitoshi |
| contents | Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on fine-tuning with large, inaccessible datasets or are training-free yet limited to generating isolated foreground elements, failing to produce a complete and coherent scene. To address this, we introduce the Training-free Noise Transplantation and Cultivation Diffusion Model (TAUE), a novel framework for layer-wise image generation that requires neither fine-tuning nor additional data. TAUE embeds global structural information from intermediate denoising latents into the initial noise to preserve spatial coherence, and integrates semantic cues through cross-layer attention sharing to maintain contextual and visual consistency across layers. Extensive experiments demonstrate that TAUE achieves state-of-the-art performance among training-free methods, delivering image quality comparable to fine-tuned models while improving inter-layer consistency. Moreover, it enables new applications, such as layout-aware editing, multi-object composition, and background replacement, indicating potential for interactive, layer-separated generation systems in real-world creative workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02580 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TAUE: Training-free Noise Transplant and Cultivation Diffusion Model Nagai, Daichi Morita, Ryugo Kitada, Shunsuke Iyatomi, Hitoshi Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on fine-tuning with large, inaccessible datasets or are training-free yet limited to generating isolated foreground elements, failing to produce a complete and coherent scene. To address this, we introduce the Training-free Noise Transplantation and Cultivation Diffusion Model (TAUE), a novel framework for layer-wise image generation that requires neither fine-tuning nor additional data. TAUE embeds global structural information from intermediate denoising latents into the initial noise to preserve spatial coherence, and integrates semantic cues through cross-layer attention sharing to maintain contextual and visual consistency across layers. Extensive experiments demonstrate that TAUE achieves state-of-the-art performance among training-free methods, delivering image quality comparable to fine-tuned models while improving inter-layer consistency. Moreover, it enables new applications, such as layout-aware editing, multi-object composition, and background replacement, indicating potential for interactive, layer-separated generation systems in real-world creative workflows. |
| title | TAUE: Training-free Noise Transplant and Cultivation Diffusion Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning |
| url | https://arxiv.org/abs/2511.02580 |