Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912018137612288 |
|---|---|
| author | Li, Guandong |
| author_facet | Li, Guandong |
| contents | Generating style-consistent images is a common task in the e-commerce field, and current methods are largely based on diffusion models, which have achieved excellent results. This paper introduces the concept of the QKV (query/key/value) level, referring to modifications in the attention maps (self-attention and cross-attention) when integrating UNet with image conditions. Without disrupting the product's main composition in e-commerce images, we aim to use a train-free method guided by pre-set conditions. This involves using shared KV to enhance similarity in cross-attention and generating mask guidance from the attention map to cleverly direct the generation of style-consistent images. Our method has shown promising results in practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_04750 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce Li, Guandong Computer Vision and Pattern Recognition Generating style-consistent images is a common task in the e-commerce field, and current methods are largely based on diffusion models, which have achieved excellent results. This paper introduces the concept of the QKV (query/key/value) level, referring to modifications in the attention maps (self-attention and cross-attention) when integrating UNet with image conditions. Without disrupting the product's main composition in e-commerce images, we aim to use a train-free method guided by pre-set conditions. This involves using shared KV to enhance similarity in cross-attention and generating mask guidance from the attention map to cleverly direct the generation of style-consistent images. Our method has shown promising results in practical applications. |
| title | Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.04750 |