GLIGEN
G
GLIGEN
Overview :
GLIGEN is an open-ended image generation model based on textual prompts, capable of generating images based on textual descriptions and bounding boxes, among other constraints. This model achieves its capability by freezing pre-trained text-to-image Diffusion model parameters and inserting new data within them. Its modular design allows for efficient training and offers strong inferential flexibility. GLIGEN supports conditional image generation in an open world and possesses strong generalization capabilities for new concepts and layouts.
Target Users :
["Conditional Image Generation","Image Editing","Image Repair"]
Total Visits: 422
Top Region: IN(74.48%)
Website Views : 88.6K
Use Cases
Input textual description 'A large cat sitting to the right of the chair' and the cat's bounding box to generate the cat's image
Input an image of a car as a style transfer condition to generate a new image of a vehicle with a similar style
Utilize the semantic segmentation map of an image as a condition to generate a new image that follows the semantic map
Features
Generating images based on textual descriptions and bounding boxes
Supports planned sampling for balancing generation quality and condition constraints
Supports style transfer based on image conditions
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase