Stylecodes: Encoding Stylistic Information For Image Generation
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917841539694592 |
|---|---|
| author | Rowles, Ciara |
| author_facet | Rowles, Ciara |
| contents | Diffusion models excel in image generation, but controlling them remains a challenge. We focus on the problem of style-conditioned image generation. Although example images work, they are cumbersome: srefs (style-reference codes) from MidJourney solve this issue by expressing a specific image style in a short numeric code. These have seen widespread adoption throughout social media due to both their ease of sharing and the fact they allow using an image for style control, without having to post the source images themselves. However, users are not able to generate srefs from their own images, nor is the underlying training procedure public. We propose StyleCodes: an open-source and open-research style encoder architecture and training procedure to express image style as a 20-symbol base64 code. Our experiments show that our encoding results in minimal loss in quality compared to traditional image-to-style techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12811 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Stylecodes: Encoding Stylistic Information For Image Generation Rowles, Ciara Computer Vision and Pattern Recognition Diffusion models excel in image generation, but controlling them remains a challenge. We focus on the problem of style-conditioned image generation. Although example images work, they are cumbersome: srefs (style-reference codes) from MidJourney solve this issue by expressing a specific image style in a short numeric code. These have seen widespread adoption throughout social media due to both their ease of sharing and the fact they allow using an image for style control, without having to post the source images themselves. However, users are not able to generate srefs from their own images, nor is the underlying training procedure public. We propose StyleCodes: an open-source and open-research style encoder architecture and training procedure to express image style as a 20-symbol base64 code. Our experiments show that our encoding results in minimal loss in quality compared to traditional image-to-style techniques. |
| title | Stylecodes: Encoding Stylistic Information For Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.12811 |