ERNIE-Image Technical Report

• URL: http://arxiv.org/abs/2605.25347v1
• Date: Mon, 25 May 2026 02:04:10 GMT
• Title: ERNIE-Image Technical Report
• Abstract summary: ERNIE-Image is an open-source text-to-image generation model built upon an 8B single-stream DiT architecture.<n>In pre-training, we combine fine-grained image categorization, rich caption annotation, aesthetic assessment, and hierarchical sampling.<n>In post-training, we apply a stabilized DPO strategy to align the model with human aesthetic preferences.
• Score: 45.08086049647297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge the gap between current open-source models and leading closed-source systems through more effective mining of large-scale pre-training data and improved supervision quality throughout training. During pre-training, we adopt a bottom-up data construction pipeline that combines fine-grained image categorization, rich caption annotation, aesthetic assessment, and hierarchical sampling. This strategy reduces data noise while preserving long-tail concepts and detailed real-world knowledge, providing a stronger foundation for complex generation tasks. In the post-training stage, we use a top-down data construction pipeline for high-demand scenarios, diversify prompt annotations to better match real user inputs, and apply a stabilized DPO strategy to align the model with human aesthetic preferences. We further train ERNIE-Image-Turbo for efficient 8-NFE generation and propose MT-DMD to mitigate capability drift during distillation. To make the model easier to use in practical scenarios, we equip it with a lightweight Prompt Enhancer that expands concise user intents into structured visual descriptions. In addition, we develop ERNIE-Image-Aes, an industrial-grade aesthetic model, together with ERNIE-Image-Aes-1K, a human-annotated benchmark for realistic aesthetic evaluation. Extensive qualitative and quantitative experiments show that ERNIE-Image achieves leading performance among open-source models and approaches top-tier commercial models in instruction following, text rendering, and aesthetic quality. We release the trained models and aesthetic resources to facilitate further academic research and technical progress in the AIGC community.

Related papers

• Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery [0.8374689870024963]
  We introduce the DataSeeds.AI sample dataset (the "DSD"), initially comprised of approximately 10,610 high-quality human peer-ranked photography images.<n>The DSD is a foundational computer vision dataset designed to usher in a new standard for commercial image datasets.<n>We document the quantitative improvements generated by the DSD on specific models against known benchmarks and make the code and the trained models used in our evaluation publicly available.
  arXiv  Detail & Related papers  (2025-06-06T01:50:28Z)
• Policy Optimized Text-to-Image Pipeline Design [73.9633527029941]
  We introduce a novel reinforcement learning-based framework for text-to-image generation.<n>Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations.<n>We then implement a two-phase training strategy: initial vocabulary training followed by GRPO-based optimization.
  arXiv  Detail & Related papers  (2025-05-27T17:50:47Z)
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset [140.1967962502411]
  We introduce a novel approach that employs a diffusion transformer to generate semantically rich CLIP image features.<n>A sequential pretraining strategy for unified models-first training on image understanding and subsequently on image generation offers practical advantages.<n>Building on our innovative model design, training recipe, and datasets, we develop BLIP3-o, a suite of state-of-the-art unified multimodal models.
  arXiv  Detail & Related papers  (2025-05-14T17:11:07Z)
• FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration [66.61201445650323]
  Existing methods suffer from a generalization bottleneck in real-world scenarios.<n>We contribute a million-scale dataset with two notable advantages over existing training data.<n>We propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios.
  arXiv  Detail & Related papers  (2024-12-02T12:08:40Z)
• High-Resolution Image Synthesis via Next-Token Prediction [19.97037318862443]
  We introduce textbfD-JEPA$cdot$T2I, an autoregressive model based on continuous tokens to generate high-quality, photorealistic images at arbitrary resolutions, up to 4K.<n>For the first time, we achieve state-of-the-art high-resolution image synthesis via next-token prediction.
  arXiv  Detail & Related papers  (2024-11-22T09:08:58Z)
• YaART: Yet Another ART Rendering Technology [119.09155882164573]
  This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences. We analyze how these choices affect both the efficiency of the training process and the quality of the generated images. We demonstrate that models trained on smaller datasets of higher-quality images can successfully compete with those trained on larger datasets.
  arXiv  Detail & Related papers  (2024-04-08T16:51:19Z)
• DINOv2: Learning Robust Visual Features without Supervision [75.42921276202522]
  This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.
  arXiv  Detail & Related papers  (2023-04-14T15:12:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.