Piece it Together: Part-Based Concepting with IP-Priors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913734739361792 |
|---|---|
| author | Richardson, Elad Goldberg, Kfir Alaluf, Yuval Cohen-Or, Daniel |
| author_facet | Richardson, Elad Goldberg, Kfir Alaluf, Yuval Cohen-Or, Daniel |
| contents | Advanced generative models excel at synthesizing images but often rely on text-based conditioning. Visual designers, however, often work beyond language, directly drawing inspiration from existing visual elements. In many cases, these elements represent only fragments of a potential concept-such as an uniquely structured wing, or a specific hairstyle-serving as inspiration for the artist to explore how they can come together creatively into a coherent whole. Recognizing this need, we introduce a generative framework that seamlessly integrates a partial set of user-provided visual components into a coherent composition while simultaneously sampling the missing parts needed to generate a plausible and complete concept. Our approach builds on a strong and underexplored representation space, extracted from IP-Adapter+, on which we train IP-Prior, a lightweight flow-matching model that synthesizes coherent compositions based on domain-specific priors, enabling diverse and context-aware generations. Additionally, we present a LoRA-based fine-tuning strategy that significantly improves prompt adherence in IP-Adapter+ for a given task, addressing its common trade-off between reconstruction quality and prompt adherence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10365 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Piece it Together: Part-Based Concepting with IP-Priors Richardson, Elad Goldberg, Kfir Alaluf, Yuval Cohen-Or, Daniel Computer Vision and Pattern Recognition Advanced generative models excel at synthesizing images but often rely on text-based conditioning. Visual designers, however, often work beyond language, directly drawing inspiration from existing visual elements. In many cases, these elements represent only fragments of a potential concept-such as an uniquely structured wing, or a specific hairstyle-serving as inspiration for the artist to explore how they can come together creatively into a coherent whole. Recognizing this need, we introduce a generative framework that seamlessly integrates a partial set of user-provided visual components into a coherent composition while simultaneously sampling the missing parts needed to generate a plausible and complete concept. Our approach builds on a strong and underexplored representation space, extracted from IP-Adapter+, on which we train IP-Prior, a lightweight flow-matching model that synthesizes coherent compositions based on domain-specific priors, enabling diverse and context-aware generations. Additionally, we present a LoRA-based fine-tuning strategy that significantly improves prompt adherence in IP-Adapter+ for a given task, addressing its common trade-off between reconstruction quality and prompt adherence. |
| title | Piece it Together: Part-Based Concepting with IP-Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.10365 |