KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913787004583936 |
|---|---|
| author | Navard, Pouyan Monsefi, Amin Karimi Zhou, Mengxi Chao, Wei-Lun Yilmaz, Alper Ramnath, Rajiv |
| author_facet | Navard, Pouyan Monsefi, Amin Karimi Zhou, Mengxi Chao, Wei-Lun Yilmaz, Alper Ramnath, Rajiv |
| contents | Recent advances in diffusion models have significantly improved text-to-image (T2I) generation, but they often struggle to balance fine-grained precision with high-level control. Methods like ControlNet and T2I-Adapter excel at following sketches by seasoned artists but tend to be overly rigid, replicating unintentional flaws in sketches from novice users. Meanwhile, coarse-grained methods, such as sketch-based abstraction frameworks, offer more accessible input handling but lack the precise control needed for detailed, professional use. To address these limitations, we propose KnobGen, a dual-pathway framework that democratizes sketch-based image generation by seamlessly adapting to varying levels of sketch complexity and user skill. KnobGen uses a Coarse-Grained Controller (CGC) module for high-level semantics and a Fine-Grained Controller (FGC) module for detailed refinement. The relative strength of these two modules can be adjusted through our knob inference mechanism to align with the user's specific needs. These mechanisms ensure that KnobGen can flexibly generate images from both novice sketches and those drawn by seasoned artists. This maintains control over the final output while preserving the natural appearance of the image, as evidenced on the MultiGen-20M dataset and a newly collected sketch dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01595 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models Navard, Pouyan Monsefi, Amin Karimi Zhou, Mengxi Chao, Wei-Lun Yilmaz, Alper Ramnath, Rajiv Computer Vision and Pattern Recognition Artificial Intelligence Recent advances in diffusion models have significantly improved text-to-image (T2I) generation, but they often struggle to balance fine-grained precision with high-level control. Methods like ControlNet and T2I-Adapter excel at following sketches by seasoned artists but tend to be overly rigid, replicating unintentional flaws in sketches from novice users. Meanwhile, coarse-grained methods, such as sketch-based abstraction frameworks, offer more accessible input handling but lack the precise control needed for detailed, professional use. To address these limitations, we propose KnobGen, a dual-pathway framework that democratizes sketch-based image generation by seamlessly adapting to varying levels of sketch complexity and user skill. KnobGen uses a Coarse-Grained Controller (CGC) module for high-level semantics and a Fine-Grained Controller (FGC) module for detailed refinement. The relative strength of these two modules can be adjusted through our knob inference mechanism to align with the user's specific needs. These mechanisms ensure that KnobGen can flexibly generate images from both novice sketches and those drawn by seasoned artists. This maintains control over the final output while preserving the natural appearance of the image, as evidenced on the MultiGen-20M dataset and a newly collected sketch dataset. |
| title | KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.01595 |