Pith. sign in

REVIEW 11 cited by

PIXART-{\delta}: Fast and Controllable Image Generation with Latent Consistency Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.05252 v1 pith:YPXVWYCP submitted 2024-01-10 cs.CV

Junsong Chen , Yue Wu , Simian Luo , Enze Xie , Sayak Paul , Ping Luo , Hang Zhao , Zhenguo Li This is my paper
classification cs.CV
keywords pixart-deltaimagesalphagenerationhigh-qualityimagemodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This technical report introduces PIXART-{\delta}, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-{\alpha} model. PIXART-{\alpha} 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-{\delta} significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-{\delta} achieves a breakthrough 0.5 seconds for generating 1024x1024 pixel images, marking a 7x improvement over the PIXART-{\alpha}. Additionally, PIXART-{\delta} 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-{\delta} 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-{\delta} offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models

    cs.CV 2025-05 unverdicted novelty 7.0 of 10

    PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.

  2. A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms

    cs.CV 2026-07 conditional novelty 6.5 of 10

    A three-layer perturbation probe shows latent selectivity is a near-binary rectified-flow fingerprint that survives ADD distillation, while score selectivity tracks distillation objective across 23 T2I models.

  3. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.

  4. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 conditional novelty 6.0 of 10

    DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.

  5. HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.

  6. Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.

  7. TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis

    cs.CV 2026-03 conditional novelty 6.0 of 10

    GeoDiT is a point-conditioned diffusion transformer that generates satellite imagery from sparse labeled points and claims to beat existing remote sensing generators on FID and SSIM.

  8. UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention

    cs.CV 2025-10 conditional novelty 5.0 of 10

    A pretrained FLUX diffusion model is adapted with local-window attention plus low-resolution global guidance, allowing 4K text-to-image generation from 1K-only training data at about 2x lower cost.

  9. NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer

    cs.CV 2025-08 conditional novelty 5.0 of 10

    NanoControl injects condition-specific key-value pairs into every attention block of Flux via a LoRA-style branch, claiming state-of-the-art controllability at 0.024% extra parameters and 0.029% extra FLOPs.

  10. DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

    cs.CV 2025-07 conditional novelty 5.0 of 10

    DC-AR generates 512x512 images in 12 masked autoregressive steps plus 20 diffusion refinement steps, using a 32x compressed 2D tokenizer, and reports gFID 5.49 on MJHQ-30K.

  11. FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation

    cs.CV 2026-06 unverdicted novelty 4.0 of 10

    FocusDiT masks non-critical query tokens before they enter the FFN in DiT models, directing capacity toward complex visual details and reporting improved text-to-image results.

Pith tools