Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.24085 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912480605765632 |
|---|---|
| author | Cho, Wonwoong Zhang, Yanxia Chen, Yan-Ying Inouye, David I. |
| author_facet | Cho, Wonwoong Zhang, Yanxia Chen, Yan-Ying Inouye, David I. |
| contents | Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, cross-modal conceptual blending for humans is prone to cognitive biases, like design fixation, which leads to local minima in the design space. In this paper, we propose a T2I diffusion adapter "IT-Blender" that can automate the blending process to enhance human creativity. Prior works related to cross-modal conceptual blending are limited in encoding a real image without loss of details or in disentangling the image and text inputs. To address these gaps, IT-Blender leverages pretrained diffusion models (SD and FLUX) to blend the latent representations of a clean reference image with those of the noisy generated image. Combined with our novel blended attention, IT-Blender encodes the real reference image without loss of details and blends the visual concept with the object specified by the text in a disentangled way. Our experiment results show that IT-Blender outperforms the baselines by a large margin in blending visual and textual concepts, shedding light on the new application of image generative models to augment human creativity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_24085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Imagine for Me: Creative Conceptual Blending of Real Images and Text via Blended Attention Cho, Wonwoong Zhang, Yanxia Chen, Yan-Ying Inouye, David I. Computer Vision and Pattern Recognition Artificial Intelligence Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, cross-modal conceptual blending for humans is prone to cognitive biases, like design fixation, which leads to local minima in the design space. In this paper, we propose a T2I diffusion adapter "IT-Blender" that can automate the blending process to enhance human creativity. Prior works related to cross-modal conceptual blending are limited in encoding a real image without loss of details or in disentangling the image and text inputs. To address these gaps, IT-Blender leverages pretrained diffusion models (SD and FLUX) to blend the latent representations of a clean reference image with those of the noisy generated image. Combined with our novel blended attention, IT-Blender encodes the real reference image without loss of details and blends the visual concept with the object specified by the text in a disentangled way. Our experiment results show that IT-Blender outperforms the baselines by a large margin in blending visual and textual concepts, shedding light on the new application of image generative models to augment human creativity. |
| title | Imagine for Me: Creative Conceptual Blending of Real Images and Text via Blended Attention |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2506.24085 |