Parameter-efficient fine-tuning for large models: A comprehensive survey

Z Han, C Gao, J Liu, J Zhang, SQ Zhang - arxiv preprint arxiv:2403.14608, 2024 - arxiv.org
Large models represent a groundbreaking advancement in multiple application fields,
enabling remarkable achievements across various tasks. However, their unprecedented …

Anydoor: Zero-shot object-level image customization

X Chen, L Huang, Y Liu, Y Shen… - Proceedings of the …, 2024 - openaccess.thecvf.com
This work presents AnyDoor a diffusion-based image generator with the power to teleport
target objects to new scenes at user-specified locations with desired shapes. Instead of …

Dynamicrafter: Animating open-domain images with video diffusion priors

J **ng, M **a, Y Zhang, H Chen, W Yu, H Liu… - … on Computer Vision, 2024 - Springer
Animating a still image offers an engaging visual experience. Traditional image animation
techniques mainly focus on animating natural scenes with stochastic dynamics (eg clouds …

Fastcomposer: Tuning-free multi-subject image generation with localized attention

G **ao, T Yin, WT Freeman, F Durand… - International Journal of …, 2024 - Springer
Diffusion models excel at text-to-image generation, especially in subject-driven generation
for personalized images. However, existing methods are inefficient due to the subject …

Champ: Controllable and consistent human image animation with 3d parametric guidance

S Zhu, JL Chen, Z Dai, Z Dong, Y Xu, X Cao… - … on Computer Vision, 2024 - Springer
In this study, we introduce a methodology for human image animation by leveraging a 3D
human parametric model within a latent diffusion framework to enhance shape alignment …

Sparsectrl: Adding sparse controls to text-to-video diffusion models

Y Guo, C Yang, A Rao, M Agrawala, D Lin… - European Conference on …, 2024 - Springer
The development of text-to-video (T2V), ie, generating videos with a given text prompt, has
been significantly advanced in recent years. However, relying solely on text prompts often …

Animate anyone: Consistent and controllable image-to-video synthesis for character animation

L Hu - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Character Animation aims to generating character videos from still images through driving
signals. Currently diffusion models have become the mainstream in visual generation …

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

L Zhang, Z Wang, Q Zhang, Q Qiu, A Pang… - ACM Transactions on …, 2024 - dl.acm.org
In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is
often hampered by the limitations of existing digital tools, which demand extensive expertise …

Photomaker: Customizing realistic human photos via stacked id embedding

Z Li, M Cao, X Wang, Z Qi… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent advances in text-to-image generation have made remarkable progress in
synthesizing realistic human photos conditioned on given text prompts. However existing …

Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning

J Ma, J Liang, C Chen, H Lu - ACM SIGGRAPH 2024 Conference …, 2024 - dl.acm.org
Recent progress in personalized image generation using diffusion models has been
significant. However, development in the area of open-domain and test-time fine-tuning-free …