Ruojun Xu, Xiaodi Wang, Yongbo Mao, Zach Cheng
We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| bytedance/StyleSSP | — | 6 of 7 |
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| box_low_pass_filter | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("590f8d1d72f3b6d0") |
| butterworth_low_pass_filter | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("4eecd5779daf3599") |
| freq_2d | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("29233e88580c636b") |
| gaussian_band_pass_filter | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("01081b1b1d96d3ec") |
| gaussian_low_pass_filter | Ran | this paper's copy was not recorded; identical code first harvested from tianxingwu/freeinit pointer only · get_code("5753a1ae1b2b2a7a") |
| get_freq_filter | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("bf3ad6a989021646") |
| ideal_low_pass_filter | Ran | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("ad6a1e55b1272d2f") |
| freq_exp | Not yet run | bytedance/StyleSSP/src/frequency_utils.py code served (permissive licence) · get_code("c5bb75e006fc5ccf") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Training-free diffusion-based methods have achieved remarkable success in style transfer, eliminating the need for extensive training or fine-tuning. However, due to the lack of targeted training for style information extraction and constraints on the content image layout, training-free methods often suffer from layout changes of original content and content leakage from style images. Through a series of experiments, we discovered that an effective startpoint in the sampling stage significantly enhances the style transfer process. Based on this discovery, we propose StyleSSP, which focuses on obtaining a better startpoint to address layout changes of original content and content leakage from style image. StyleSSP comprises two key components: (1) Frequency Manipulation: To improve content preservation, we reduce the low-frequency components of the DDIM latent, allowing the sampling stage to pay more attention to the layout of content images; and (2) Negative Guidance via Inversion: To mitigate the content leakage from style image, we employ negative guidance in the inversion stage to ensure that the startpoint of the sampling stage is distanced from the content of style image. Experiments show that Sty-leSSP surpasses previous training-free style transfer baselines, particularly in preserving original content and minimizing the content leakage from style image. Project page: https://github.com/bytedance/StyleSSP.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.11319")
get_code_for_paper("2501.11319")
have("2501.11319")
Connect an agent — have() is free.