Downloads · 30 days
0
Detector_Guidance
luping-liu/Detector_Guidance
Detector_Guidance is a machine learning model from luping-liu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
by Luping Liu<sup1</sup, Zijian Zhang<sup1</sup, Yi Ren<sup2</sup, Rongjie Huang<sup1</sup, Zhou Zhao<sup1</sup.
Access
Public
Updated Feb 7, 2024
Repo size
92 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.ckpt92 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Feb 7, 2024
- Updated
- Feb 7, 2024
- SHA
- 3c87bf95
Model card
From the Hugging Face model README
Detector Guidance for Multi-Object Text-to-Image Generation
by Luping Liu<sup>1</sup>, Zijian Zhang<sup>1</sup>, Yi Ren<sup>2</sup>, Rongjie Huang<sup>1</sup>, Zhou Zhao<sup>1</sup>.
<sup>1</sup>Zhejiang University, <sup>2</sup>ByteDance
In this work, we introduce Detector Guidance (DG), which integrates a latent object detection model to separate different objects during the generation process. More precisely, DG first performs latent object detection on cross-attention maps (CAMs) to obtain object information. Based on this information, DG then masks conflicting prompts and enhances related prompts by manipulating the following CAMs. Human evaluations demonstrate that DG provides an 8-22% advantage in preventing the amalgamation of conflicting concepts and ensuring that each object possesses its unique region without any human involvement and additional iterations.
- License
- apache-2.0
- Created
- Feb 7, 2024
- Updated
- Feb 7, 2024