Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers
cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/ljjcoder/Restoring-Semantic-Fidelity
Terminology
Sources
- Demystifying MMD GANs
- Classifier-Free Diffusion Guidance
- LinFusion: 1 GPU, 1 Minute, 16K Image
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
- Denoising Diffusion Implicit Models
- Ultra-Resolution Adaptation with Ease
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