Stylistic Attribute Control in Latent Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911644260499456 |
|---|---|
| author | Reimann, Max Buchheim, Benito Döllner, Jürgen |
| author_facet | Reimann, Max Buchheim, Benito Döllner, Jürgen |
| contents | Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained parametric control of stylistic attributes in latent diffusion models by learning disentangled editing directions from synthetic datasets. We use guidance composition to close the domain gap between stylistically finetuned and foundation models, preserving the original image semantics while applying stylistic adjustments. To ensure consistent edits, we introduce a training regularization loss and enhance DDIM inversion with optimized null-conditional embeddings for real image editing. We validate our approach by learning from stylistically filtered synthetic datasets varying a range of stylistic attributes, including outlines, local contrast, watercolorization effects, and geometric patterns. Our evaluations demonstrate that compared to current text-based editing techniques, our method offers well-integrated, more precise and continuously adjustable stylistic modifications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02583 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stylistic Attribute Control in Latent Diffusion Models Reimann, Max Buchheim, Benito Döllner, Jürgen Computer Vision and Pattern Recognition Text-to-image diffusion models have revolutionized image synthesis and editing, but precise control over stylistic attributes remains a challenge, often causing unintended content modifications. We propose an approach for fine-grained parametric control of stylistic attributes in latent diffusion models by learning disentangled editing directions from synthetic datasets. We use guidance composition to close the domain gap between stylistically finetuned and foundation models, preserving the original image semantics while applying stylistic adjustments. To ensure consistent edits, we introduce a training regularization loss and enhance DDIM inversion with optimized null-conditional embeddings for real image editing. We validate our approach by learning from stylistically filtered synthetic datasets varying a range of stylistic attributes, including outlines, local contrast, watercolorization effects, and geometric patterns. Our evaluations demonstrate that compared to current text-based editing techniques, our method offers well-integrated, more precise and continuously adjustable stylistic modifications. |
| title | Stylistic Attribute Control in Latent Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02583 |