# PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models

arXiv: https://arxiv.org/abs/2401.05252 · HTML: https://mlsanity.com/paper/2401.05252/

## Key facts

- Cited by 141 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 10 Jan 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 9 of 9)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [LCM-LoRA: A Universal Stable-Diffusion Acceleration Module](https://mlsanity.com/paper/2311.05556/) (2023)
- [On the Importance of Noise Scheduling for Diffusion Models](https://mlsanity.com/paper/2301.10972/) (2023)

## Built on by (most cited first, 30 of 141)

- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control](https://mlsanity.com/paper/2407.12781/) (2024)
- [AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers](https://mlsanity.com/paper/2411.18673/) (2024)
- [CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models](https://mlsanity.com/paper/2406.08070/) (2024)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)
- [HART: Efficient Visual Generation with Hybrid Autoregressive Transformer](https://mlsanity.com/paper/2410.10812/) (2024)
- [OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models](https://mlsanity.com/paper/2502.01061/) (2025)
- [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://mlsanity.com/paper/2410.19355/) (2024)
- [Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models](https://mlsanity.com/paper/2410.02416/) (2024)
- [Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond](https://mlsanity.com/paper/2405.03520/) (2024)
- [Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control](https://mlsanity.com/paper/2503.14492/) (2025)
- [Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders](https://mlsanity.com/paper/2412.17808/) (2024)
- [Latent Diffusion Model without Variational Autoencoder](https://mlsanity.com/paper/2510.15301/) (2025)
- [SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://mlsanity.com/paper/2503.09641/) (2025)
- [Training-free and Adaptive Sparse Attention for Efficient Long Video Generation](https://mlsanity.com/paper/2502.21079/) (2025)
- [TIIF-Bench: How Does Your T2I Model Follow Your Instructions?](https://mlsanity.com/paper/2506.02161/) (2025)
- [Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model](https://mlsanity.com/paper/2404.09967/) (2024)
- [FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification](https://mlsanity.com/paper/2410.10356/) (2024)
- [Dynamic Diffusion Transformer](https://mlsanity.com/paper/2410.03456/) (2024)
- [ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation](https://mlsanity.com/paper/2406.01586/) (2024)
- [SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher](https://mlsanity.com/paper/2408.14176/) (2024)
- [ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer](https://mlsanity.com/paper/2412.07720/) (2024)
- [Vivid-ZOO: Multi-View Video Generation with Diffusion Model](https://mlsanity.com/paper/2406.08659/) (2024)
- [EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation](https://mlsanity.com/paper/2412.18150/) (2024)
- [Reangle-A-Video: 4D Video Generation as Video-to-Video Translation](https://mlsanity.com/paper/2503.09151/) (2025)
- [DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation](https://mlsanity.com/paper/2411.11252/) (2024)
- [OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation](https://mlsanity.com/paper/2508.19209/) (2025)
- [DiVE: DiT-based Video Generation with Enhanced Control](https://mlsanity.com/paper/2409.01595/) (2024)
- [STAR: Scale-wise Text-conditioned AutoRegressive image generation](https://mlsanity.com/paper/2406.10797/) (2024)

## Abstract (arXiv)

This technical report introduces PIXART-δ, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-α model. PIXART-α is recognized for its ability to generate high-quality images of 1024px resolution through a remarkably efficient training process. The integration of LCM in PIXART-δ significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-δ achieves a breakthrough 0.5 seconds for generating 1024x1024 pixel images, marking a 7x improvement over the PIXART-α. Additionally, PIXART-δ is designed to be efficiently trainable on 32GB V100 GPUs within a single day. With its 8-bit inference capability (von Platen et al., 2023), PIXART-δ can synthesize 1024px images within 8GB GPU memory constraints, greatly enhancing its usability and accessibility. Furthermore, incorporating a ControlNet-like module enables fine-grained control over text-to-image diffusion models. We introduce a novel ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation. As a state-of-the-art, open-source image generation model, PIXART-δ offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.