LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
Linoy Tsaban, Apolinário Passos
LEDITS combines Edit Friendly DDPM inversion and Semantic Guidance to enable versatile and efficient real-image editing using text prompts.
Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Diffusion for World Modeling: Visual Details Matter in Atari
Eloi Alonso, Adam Jelley, Vincent Micheli +4 authors
DIAMOND, a reinforcement learning agent using a diffusion world model, achieves top performance on Atari 100k by capturing visual details effectively.
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
Kai Yang, Jian Tao, Jiafei Lyu +6 authors
D3PO method directly fine-tunes diffusion models using human feedback without requiring a separate reward model, reducing computational cost and improving image quality.
DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
Yifeng Ma, Shiwei Zhang, Jiayu Wang +3 authors
DreamTalk enables expressive talking head generation using diffusion models with specialized components for denoising, lip-sync, and style prediction.
Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis
Bichen Wu, Ching-Yao Chuang, Xiaoyan Wang +6 authors
Fairy, an adaptation of image-editing diffusion models for video editing, uses anchor-based cross-frame attention to enhance temporal coherence and efficiency, outperforming existing methods.
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
Koorosh Roohi, Javad Rajabi, Andrew Fleet +1 authors
PhotoQuilt is a training-free framework that generates high-resolution photomosaics by combining global layout composition with separate tile generation in latent space, overcoming limitations of diffusion models in balancing local detail and global structure.
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
Zeju Qiu, Weiyang Liu, Haiwen Feng +6 authors
Orthogonal Finetuning and Constrained Orthogonal Finetuning methods enhance text-to-image diffusion models by preserving hyperspherical energy and improving stability, leading to better generation quality and speed.
Generate Anything Anywhere in Any Scene
Yuheng Li, Haotian Liu, Yangming Wen +1 authors
A text-to-image diffusion model is enhanced with adapter layers and regionally-guided sampling to achieve controlled generation of personalized objects with high fidelity.
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin +8 authors
Wonder3D leverages cross-domain diffusion models and geometry-aware normal fusion for high-quality, efficient, and consistent 3D mesh generation from single-view images.
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
Yujun Shi, Chuhui Xue, Jiachun Pan +3 authors
DragDiffusion extends interactive point-based image editing to diffusion models, offering precise spatial control and high-quality editing across diverse scenarios.
MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies
Ke Chen, Yusong Wu, Haohe Liu +3 authors
A text-to-music model named MusicLDM, based on Stable Diffusion and AudioLDM, overcomes limitations in music data and plagiarism with beat tracking and mixup strategies, enhancing music quality, novelty, and text correspondence.
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
Zhengyi Wang, Cheng Lu, Yikai Wang +4 authors
Variational score distillation addresses issues in text-to-3D generation by modeling 3D parameters as random variables, improving sample quality and diversity.
Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
Yuxin Wen, John Kirchenbauer, Jonas Geiping +1 authors
A novel technique called Tree-Ring Watermarking robustly fingerprints diffusion model outputs by embedding a pattern into the initial noise vector and is invariant to various image transformations.
HiFA: High-fidelity Text-to-3D with Advanced Diffusion Guidance
Joseph Zhu, Peiye Zhuang
Reformulating optimization loss with diffusion prior and introducing depth supervision improve text-to-3D synthesis quality and multi-view consistency.
上升最快
近 6 个月1
56 篇论文
2
38 篇论文
3
mllmsNEW
29 篇论文
4
26 篇论文
5
17 篇论文
6
15 篇论文
7
distillationNEW
14 篇论文
8
ditNEW
13 篇论文
9
zero-shotNEW
12 篇论文
10
12 篇论文
11
12 篇论文
12
11 篇论文
13
11 篇论文
14
10 篇论文
15
10 篇论文
16
10 篇论文
17
10 篇论文
18
chain-of-thought+500%
30 篇论文
19
rlvr+400%
15 篇论文
20
12 篇论文
最热方向
按总量1
322 篇论文
2
221 篇论文
3
167 篇论文
4
94 篇论文
5
76 篇论文
7
75 篇论文
8
61 篇论文
9
10
49 篇论文
11
44 篇论文
12
40 篇论文
13
38 篇论文
14
38 篇论文
15
35 篇论文
16
35 篇论文
17
33 篇论文
18
31 篇论文
19
30 篇论文
20
29 篇论文
21
29 篇论文
22
29 篇论文
23
29 篇论文
24
25
27 篇论文
26
27 篇论文
27
26 篇论文
28
26 篇论文
29
25 篇论文
30
24 篇论文
31
23 篇论文
32
23 篇论文
33
23 篇论文
34
23 篇论文
35
23 篇论文
36
22 篇论文
37
20 篇论文
38
20 篇论文
39
20 篇论文
40
20 篇论文
41
20 篇论文
42
43
19 篇论文
44
19 篇论文
45
19 篇论文
47
18 篇论文
49
50
18 篇论文
51
52
17 篇论文
53
17 篇论文
54
16 篇论文
55
16 篇论文
56
16 篇论文
57
16 篇论文
58
16 篇论文
59
16 篇论文
60
16 篇论文