ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-instance Generation
- 14 September 2026
- book chapter
- Published by Springer Nature
- p. 137-155
Abstract
No abstract availableKeywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Be Yourself: Bounded Attention for Multi-subject Text-to-Image Generation2024
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- PIXART-$\Sigma $: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation2024
- InstanceDiffusion: Instance-Level Control for Image Generation2024
- CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models2024
- NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging2024
- Grounded Text-to-Image Synthesis with Attention Refocusing2024
- MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis2024
- GLIGEN: Open-Set Grounded Text-to-Image Generation2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022