Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910468417781760 |
|---|---|
| author | Zheng, Candi Lan, Yuan |
| author_facet | Zheng, Candi Lan, Yuan |
| contents | Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_07586 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale Zheng, Candi Lan, Yuan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Data Analysis, Statistics and Probability Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling. |
| title | Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2312.07586 |