FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917067506057216 |
|---|---|
| author | Lin, Jiang Chen, Xinyu Wu, Song Zhang, Zhiqiu Zhang, Jizhi Wang, Ye Tang, Qiang Wang, Qian Yang, Jian Yi, Zili |
| author_facet | Lin, Jiang Chen, Xinyu Wu, Song Zhang, Zhiqiu Zhang, Jizhi Wang, Ye Tang, Qiang Wang, Qian Yang, Jian Yi, Zili |
| contents | Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction Lin, Jiang Chen, Xinyu Wu, Song Zhang, Zhiqiu Zhang, Jizhi Wang, Ye Tang, Qiang Wang, Qian Yang, Jian Yi, Zili Computer Vision and Pattern Recognition Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present FreeControl, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs one-step attention extraction from a single, optimally chosen key timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce Latent-Condition Decoupling (LCD): a principled separation of the key timestep and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources - enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control, enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at approximately 5 percent additional cost. |
| title | FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.05219 |