Seedream 3.0 Technical Report

• URL: http://arxiv.org/abs/2504.11346v2
• Date: Wed, 16 Apr 2025 16:23:31 GMT
• Title: Seedream 3.0 Technical Report
• Authors: Yu Gao, Lixue Gong, Qiushan Guo, Xiaoxia Hou, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, Wei Liu, Yichun Shi, Shiqi Sun, Yu Tian, Zhi Tian, Peng Wang, Rui Wang, Xuanda Wang, Xun Wang, Ye Wang, Guofeng Wu, Jie Wu, Xin Xia, Xuefeng Xiao, Zhonghua Zhai, Xinyu Zhang, Qi Zhang, Yuwei Zhang, Shijia Zhao, Jianchao Yang, Weilin Huang,
• Abstract summary: Seedream 3.0 is a high-performance Chinese-English bilingual image generation foundation model.<n>We develop several technical improvements to address existing challenges in Seedream 2.0.<n>Seedream 3.0 provides native high-resolution output (up to 2K) allowing it to generate images with high visual quality.
• Score: 62.85849652170507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts, fine-grained typography generation, suboptimal visual aesthetics and fidelity, and limited image resolutions. Specifically, the advancements of Seedream 3.0 stem from improvements across the entire pipeline, from data construction to model deployment. At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework. Furthermore, we adopt several effective techniques such as mixed-resolution training, cross-modality RoPE, representation alignment loss, and resolution-aware timestep sampling in the pre-training phase. During the post-training stage, we utilize diversified aesthetic captions in SFT, and a VLM-based reward model with scaling, thereby achieving outputs that well align with human preferences. Furthermore, Seedream 3.0 pioneers a novel acceleration paradigm. By employing consistent noise expectation and importance-aware timestep sampling, we achieve a 4 to 8 times speedup while maintaining image quality. Seedream 3.0 demonstrates significant improvements over Seedream 2.0: it enhances overall capabilities, in particular for text-rendering in complicated Chinese characters which is important to professional typography generation. In addition, it provides native high-resolution output (up to 2K), allowing it to generate images with high visual quality.

Related papers

• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos. These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model [69.09404597939744]
  Seedream 2.0 is a native Chinese-English bilingual image generation foundation model.<n>It adeptly manages text prompt in both Chinese and English, supporting bilingual image generation and text rendering.<n>It is integrated with a self-developed bilingual large language model as a text encoder, allowing it to learn native knowledge directly from massive data.
  arXiv  Detail & Related papers  (2025-03-10T17:58:33Z)
• TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models [69.0220314849478]
  TripoSG is a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.
  arXiv  Detail & Related papers  (2025-02-10T16:07:54Z)
• DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation [46.22939360256696]
  We present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets. DreamClear, is a DiT-based image restoration model. It utilizes the generative priors of text-to-image (T2I) diffusion models and the robust perceptual capabilities of multi-modal large language models (MLLMs) to achieve restoration.
  arXiv  Detail & Related papers  (2024-10-24T11:57:20Z)
• Flex3D: Feed-Forward 3D Generation With Flexible Reconstruction Model And Input View Curation [61.040832373015014]
  We propose Flex3D, a novel framework for generating high-quality 3D content from text, single images, or sparse view images. We employ a fine-tuned multi-view image diffusion model and a video diffusion model to generate a pool of candidate views, enabling a rich representation of the target 3D object. In the second stage, the curated views are fed into a Flexible Reconstruction Model (FlexRM), built upon a transformer architecture that can effectively process an arbitrary number of inputs.
  arXiv  Detail & Related papers  (2024-10-01T17:29:43Z)
• PlacidDreamer: Advancing Harmony in Text-to-3D Generation [20.022078051436846]
  PlacidDreamer is a text-to-3D framework that harmonizes multi-view generation and text-conditioned generation. It employs a novel score distillation algorithm to achieve balanced saturation.
  arXiv  Detail & Related papers  (2024-07-19T02:00:04Z)
• Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data [80.92268916571712]
  A critical bottleneck is the scarcity of high-quality 3D objects with detailed captions. We propose Bootstrap3D, a novel framework that automatically generates an arbitrary quantity of multi-view images. We have generated 1 million high-quality synthetic multi-view images with dense descriptive captions.
  arXiv  Detail & Related papers  (2024-05-31T17:59:56Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [111.16358607889609]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation.<n>For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• 3DGen: Triplane Latent Diffusion for Textured Mesh Generation [17.178939191534994]
  A triplane VAE learns latent representations of textured meshes and a conditional diffusion model generates the triplane features. For the first time this architecture allows conditional and unconditional generation of high quality textured or untextured 3D meshes. It outperforms previous work substantially on image-conditioned and unconditional generation on mesh quality as well as texture generation.
  arXiv  Detail & Related papers  (2023-03-09T16:18:14Z)

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.