Compara mètodes
Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.
| Models de difusió latents× | QLoRA× | |
|---|---|---|
| Camp | Aprenentatge profund | Aprenentatge profund |
| Família | Machine learning | Machine learning |
| Any d'origen≠ | 2022 | 2023 |
| Autor original≠ | Robin Rombach | Tim Dettmers |
| Tipus≠ | Neural network architecture | Training methodology |
| Font seminal≠ | Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695). DOI ↗ | Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗ |
| Àlies≠ | LDM, Stable Diffusion, Latent Diffusion | QLoRA, Quantized LoRA |
| Relacionats | 4 | 4 |
| Resum≠ | Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality. | QLoRA is an efficient fine-tuning method introduced by Dettmers et al. in 2023 that enables fine-tuning large language models using quantization and low-rank adaptation. By combining 4-bit quantization with LoRA, QLoRA reduces memory requirements by 75%, enabling fine-tuning of 65B-parameter models on single GPUs. |
| ScholarGateConjunt de dades ↗ |
|
|