DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
cs.CV, cs.LG
Submitted: 2026-05-16
Updated: 2026-11-06
Code: https://github.com/black-forest-labs/flux
Terminology
Sources
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- Token Merging: Your ViT But Faster
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- Microsoft COCO Captions: Data Collection and Evaluation Server
- MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Gaussian Error Linear Units (GELUs)
- Classifier-Free Diffusion Guidance
- ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- GPT-4o System Card
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- Progressive Distillation for Fast Sampling of Diffusion Models
- Denoising Diffusion Implicit Models
- Improved Techniques for Training Consistency Models
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
- IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
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