Compositional Image Synthesis with Inference-Time Scaling
"文本到图像生成" 相关文章
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
Fine-tuning Flow Matching Generative Models with Intermediate Feedback
Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
CharCom: Composable Identity Control for Multi-Character Story Illustration
OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
Text-to-Image: Diffusion, Text Conditioning, Guidance, Latent Space
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
SemanticControl: A Training-Free Approach for Handling Loosely Aligned Visual Conditions in ControlNet
Automated Prompt Generation for Creative and Counterfactual Text-to-image Synthesis
Mitigating Catastrophic Forgetting and Mode Collapse in Text-to-Image Diffusion via Latent Replay
MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation
Multimodal LLMs as Customized Reward Models for Text-to-Image Generation
LSSGen: Leveraging Latent Space Scaling in Flow and Diffusion for Efficient Text to Image Generation
