Guidance Free Image Editing via Explicit Conditioning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917964961284096 |
|---|---|
| author | Noroozi, Mehdi Ramos, Alberto Gil Morreale, Luca Chavhan, Ruchika Chadwick, Malcolm Mehrotra, Abhinav Bhattacharya, Sourav |
| author_facet | Noroozi, Mehdi Ramos, Alberto Gil Morreale, Luca Chavhan, Ruchika Chadwick, Malcolm Mehrotra, Abhinav Bhattacharya, Sourav |
| contents | Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image editing tasks, resulting in excessive computational costs. This paper introduces a novel conditioning technique to ease the computational burden of the well-established guidance techniques, thereby significantly improving the inference time of diffusion models. We present Explicit Conditioning (EC) of the noise distribution on the input modalities to achieve this. Intuitively, we model the noise to guide the conditional diffusion model during the diffusion process. We present evaluations on image editing tasks and demonstrate that EC outperforms CFG in generating diverse high-quality images with significantly reduced computations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17593 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guidance Free Image Editing via Explicit Conditioning Noroozi, Mehdi Ramos, Alberto Gil Morreale, Luca Chavhan, Ruchika Chadwick, Malcolm Mehrotra, Abhinav Bhattacharya, Sourav Computer Vision and Pattern Recognition Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image editing tasks, resulting in excessive computational costs. This paper introduces a novel conditioning technique to ease the computational burden of the well-established guidance techniques, thereby significantly improving the inference time of diffusion models. We present Explicit Conditioning (EC) of the noise distribution on the input modalities to achieve this. Intuitively, we model the noise to guide the conditional diffusion model during the diffusion process. We present evaluations on image editing tasks and demonstrate that EC outperforms CFG in generating diverse high-quality images with significantly reduced computations. |
| title | Guidance Free Image Editing via Explicit Conditioning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.17593 |