ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Finjusteret diffusionsmodel

En finjusteret diffusionsmodel tilpasser en stor forhåndstrænet denoising-diffusionsmodel – såsom Stable Diffusion eller DALL-E – til et specifikt emne, en stil eller et domæne ved at fortsætte træningen på et lille, kurateret datasæt. Teknikker som DreamBooth, tekstuel inversion og LoRA gør denne tilpasning mulig på forbrugerhardware, samtidig med at den generelle generative kapacitet bevares.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023). DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 22500–22510. DOI: 10.1109/CVPR52729.2023.02155
  2. Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. Advances in Neural Information Processing Systems (NeurIPS), 33, 6840–6851. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Fine-Tuned Denoising Diffusion Probabilistic Model. ScholarGate. https://scholargate.app/da/deep-learning/fine-tuned-diffusion-model

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Refereret af

ScholarGateFine-Tuned Diffusion Model (Fine-Tuned Denoising Diffusion Probabilistic Model). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/fine-tuned-diffusion-model · Datasæt: https://doi.org/10.5281/zenodo.20539026