Direct Trajectory Optimization for Inference-Time Alignment of Text-to-Image Diffusion Models
cs.CV, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-10
Code: https://github.com/black-forest-labs/flux
Terminology
Sources
- Building Normalizing Flows with Stochastic Interpolants
- Training Diffusion Models with Reinforcement Learning
- Seedream 3.0 Technical Report
- Classifier-Free Diffusion Guidance
- Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
- Evaluating Text-to-Visual Generation with Image-to-Text Generation
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
- Diffusion Model Alignment Using Direct Preference Optimization
- Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
- Unified Reward Model for Multimodal Understanding and Generation
- Unified Personalized Reward Model for Vision Generation
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Re-Thinking the Automatic Evaluation of Image-Text Alignment in Text-to-Image Models
- MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs