HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts
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_ | 1866909308517613568 |
|---|---|
| author | Liu, Xinyu He, Yingqing Guo, Lanqing Li, Xiang Jin, Bu Li, Peng Li, Yan Chan, Chi-Min Chen, Qifeng Xue, Wei Luo, Wenhan Liu, Qifeng Guo, Yike |
| author_facet | Liu, Xinyu He, Yingqing Guo, Lanqing Li, Xiang Jin, Bu Li, Peng Li, Yan Chan, Chi-Min Chen, Qifeng Xue, Wei Luo, Wenhan Liu, Qifeng Guo, Yike |
| contents | The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02919 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts Liu, Xinyu He, Yingqing Guo, Lanqing Li, Xiang Jin, Bu Li, Peng Li, Yan Chan, Chi-Min Chen, Qifeng Xue, Wei Luo, Wenhan Liu, Qifeng Guo, Yike Computer Vision and Pattern Recognition The potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality. |
| title | HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.02919 |