Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17740 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914957952548864 |
|---|---|
| author | Zhang, Jinghao Qian, Wen Luo, Hao Wang, Fan Zhao, Feng |
| author_facet | Zhang, Jinghao Qian, Wen Luo, Hao Wang, Fan Zhao, Feng |
| contents | Diffusion models have made compelling progress on facilitating high-throughput daily production. Nevertheless, the appealing customized requirements are remain suffered from instance-level finetuning for authentic fidelity. Prior zero-shot customization works achieve the semantic consistence through the condensed injection of identity features, while addressing detailed low-level signatures through complex model configurations and subject-specific fabrications, which significantly break the statistical coherence within the overall system and limit the applicability across various scenarios. To facilitate the generic signature concentration with rectified efficiency, we present \textbf{AnyLogo}, a zero-shot region customizer with remarkable detail consistency, building upon the symbiotic diffusion system with eliminated cumbersome designs. Streamlined as vanilla image generation, we discern that the rigorous signature extraction and creative content generation are promisingly compatible and can be systematically recycled within a single denoising model. In place of the external configurations, the gemini status of the denoising model promote the reinforced subject transmission efficiency and disentangled semantic-signature space with continuous signature decoration. Moreover, the sparse recycling paradigm is adopted to prevent the duplicated risk with compressed transmission quota for diversified signature stimulation. Extensive experiments on constructed logo-level benchmarks demonstrate the effectiveness and practicability of our methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17740 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status Zhang, Jinghao Qian, Wen Luo, Hao Wang, Fan Zhao, Feng Computer Vision and Pattern Recognition Diffusion models have made compelling progress on facilitating high-throughput daily production. Nevertheless, the appealing customized requirements are remain suffered from instance-level finetuning for authentic fidelity. Prior zero-shot customization works achieve the semantic consistence through the condensed injection of identity features, while addressing detailed low-level signatures through complex model configurations and subject-specific fabrications, which significantly break the statistical coherence within the overall system and limit the applicability across various scenarios. To facilitate the generic signature concentration with rectified efficiency, we present \textbf{AnyLogo}, a zero-shot region customizer with remarkable detail consistency, building upon the symbiotic diffusion system with eliminated cumbersome designs. Streamlined as vanilla image generation, we discern that the rigorous signature extraction and creative content generation are promisingly compatible and can be systematically recycled within a single denoising model. In place of the external configurations, the gemini status of the denoising model promote the reinforced subject transmission efficiency and disentangled semantic-signature space with continuous signature decoration. Moreover, the sparse recycling paradigm is adopted to prevent the duplicated risk with compressed transmission quota for diversified signature stimulation. Extensive experiments on constructed logo-level benchmarks demonstrate the effectiveness and practicability of our methods. |
| title | AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17740 |