REVIEW 2 cited by
StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on the denoising process to accomplish image control. However these conditions are not aligned with the word embedding space, leading to interference between image and text control conditions and the potential loss of semantic information from the text prompt. Addressing this issue involves two key challenges. Firstly, how to inject the style representation without compromising the effectiveness of text representation in control. Secondly, how to obtain the accurate style representation from a single reference image. To tackle these challenges, we introduce StyleTokenizer, a zero-shot style control image generation method that aligns style representation with text representation using a style tokenizer. This alignment effectively minimizes the impact on the effectiveness of text prompts. Furthermore, we collect a well-labeled style dataset named Style30k to train a style feature extractor capable of accurately representing style while excluding other content information. Experimental results demonstrate that our method fully grasps the style characteristics of the reference image, generating appealing images that are consistent with both the target image style and text prompt. The code and dataset are available at https://github.com/alipay/style-tokenizer.
Forward citations
Cited by 2 Pith papers
-
AIComposer: Any Style and Content Image Composition via Feature Integration
A nearly training-free SDXL pipeline composes foreground content with background style using a small MLP that merges CLIP image features, removing the need for text prompts.
-
OmniStyle: Filtering High Quality Style Transfer Data at Scale
A new million-triplet dataset and a diffusion transformer model that performs text-guided and image-guided style transfer, with a filtering pipeline used to curate high-quality training examples.
Discussion (0). Continue with ORCID to comment.