.png){kind=icon}
返回
Training-Free Consistent Text-to-Image Generation
.png){kind=icon}
OA
AI
DOI：10.1145/3658157.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts remains challenging. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects or add image conditioning to the model. These methods require lengthy per-subject optimization or large-scale pre-training. Moreover, they struggle to align generated images with text prompts and face difficulties in portraying multiple subjects. Here, we present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model. We introduce a subject-driven shared attention block and correspondence-based feature injection to promote subject consistency between images. Additionally, we develop strategies to encourage layout diversity while maintaining subject consistency. We compare ConsiStory to a range of baselines, and demonstrate state-of-the-art performance on subject consistency and text alignment, without requiring a single optimization step. Finally, ConsiStory can naturally extend to multi-subject scenarios, and even enable training-free personalization for common objects.
Keyword:
Text-to-Image
Consistent
Story
Diffusion
Training-Free
期刊
IF:
9.5
论文数:
4.7K
被引数:
3.6W
机构
引用论文
.png){kind=icon}
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models基于编码器的域调整，用于文本到图像模型的快速个性化OAAI
OAAI分享收藏
查看更多内容