AIHOT 于 2026-08-17 收录了“像素空间文生图扩散模型训练实证研究：潜空间到像素空间策略带来 3.18-4.75 倍推理加速”这一公开动态。以下先呈现从来源页面抓取的正文，再给出 AIHOT 摘要与 TopoReduce 编辑解读。
PUBLIC SOURCE CONTENT
已抓取公开正文公开原文内容
[2608.16887] An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Computer Science > Computer Vision and Pattern Recognition
arXiv:2608.16887 (cs)
-
[Submitted on 17 Aug 2026]
Title:An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Authors:Dengyang Jiang, Ruoyi Du, Zhennan Chen, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Xiangpeng Yang, Huanqia Cai, Aiming Hao, Yuming Jiang, Peng Gao, Harry Yang, Steven Hoi
View a PDF of the paper titled An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models, by Dengyang Jiang and 12 other authors
View PDF
HTML (experimental)
Abstract:This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on small-scale or class-conditional settings. Consequently, a practical recipe for training pixel-space models that rival or exceed well-established latent-space counterparts remains elusive. Through a comprehensive empirical study, we first observe that direct large-scale pre-training in pixel space converges substantially more slowly than in latent space. This observation motivates a latent-to-pixel strategy that acquires generative priors efficiently in latent space and transitions to pixel space during post-training. We then systematically investigate the key design choices governing this transition, including weight initialization, data composition, prediction target, decoder architecture, and noise schedule, and identify a practical recipe that makes the resulting pixel-space models match or outperform their latent-space counterparts while delivering 3.18 to 4.75 times end-to-end inference speedups. We hope that our findings provide useful empirical insights and practical guidelines for future research on pixel-space generation.
Comments:
Z-Image-Pixel & Empirical Insight of Training Pixel-Space Diffusion Models
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as:
arXiv:2608.16887 [cs.CV]
(or
arXiv:2608.16887v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.16887
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Dengyang Jiang [view email]
[v1]
Mon, 17 Aug 2026 17:59:25 UTC (9,609 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models, by Dengyang Jiang and 12 other authors
- View PDF
- HTML (experimental)
- TeX Source
view license
Current browse context:
cs.CV
< prev
|
next >
new
|
recent
| 2026-08
Change to browse by:
cs
References & Citations
- NASA ADS
- Google Scholar
- Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
- Author
- Venue
- Institution
- Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)
arXiv:2608.16887 (cs)
-
[Submitted on 17 Aug 2026]
Title:An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Authors:Dengyang Jiang, Ruoyi Du, Zhennan Chen, Dongyang Liu, Zanyi Wang, Mingzhe Zheng, Xiangpeng Yang, Huanqia Cai, Aiming Hao, Yuming Jiang, Peng Gao, Harry Yang, Steven Hoi
View a PDF of the paper titled An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models, by Dengyang Jiang and 12 other authors
View PDF
HTML (experimental)
Abstract:This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on small-scale or class-conditional settings. Consequently, a practical recipe for training pixel-space models that rival or exceed well-established latent-space counterparts remains elusive. Through a comprehensive empirical study, we first observe that direct large-scale pre-training in pixel space converges substantially more slowly than in latent space. This observation motivates a latent-to-pixel strategy that acquires generative priors efficiently in latent space and transitions to pixel space during post-training. We then systematically investigate the key design choices governing this transition, including weight initialization, data composition, prediction target, decoder architecture, and noise schedule, and identify a practical recipe that makes the resulting pixel-space models match or outperform their latent-space counterparts while delivering 3.18 to 4.75 times end-to-end inference speedups. We hope that our findings provide useful empirical insights and practical guidelines for future research on pixel-space generation.
Comments:
Z-Image-Pixel & Empirical Insight of Training Pixel-Space Diffusion Models
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as:
arXiv:2608.16887 [cs.CV]
(or
arXiv:2608.16887v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.16887
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Dengyang Jiang [view email]
[v1]
Mon, 17 Aug 2026 17:59:25 UTC (9,609 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models, by Dengyang Jiang and 12 other authors
- View PDF
- HTML (experimental)
- TeX Source
view license
Current browse context:
cs.CV
< prev
|
next >
new
|
recent
| 2026-08
Change to browse by:
cs
References & Citations
- NASA ADS
- Google Scholar
- Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
- Author
- Venue
- Institution
- Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)
AIHOT 摘要
一项实证研究发现，像素空间扩散模型直接大规模预训练收敛速度远慢于潜空间模型，由此提出“潜空间到像素空间”策略：先在潜空间高效获取生成先验，再在后训练阶段转向像素空间。该策略结合权重初始化、数据构成、预测目标、解码器架构与噪声调度等设计选择，使像素空间模型达到或超越潜空间模型，并实现 3.18 至 4.75 倍的端到端推理加速。
为什么值得关注
它把像素空间扩散模型的训练拆成先潜空间后像素空间过渡，并定位影响加速倍数的关键设计，为低延迟图像生成提供了一条绕开从头训练的可行路径。
工程化解读
从 TopoReduce 的工程视角看，这条信息属于“论文与研究”主题。它的价值不只在于一个新产品或新观点本身，还在于说明 AI 系统正在如何影响模型接入、智能体协作、研发流程、基础设施和团队决策。实际采用前，应结合原文确认版本、适用范围、价格和运行条件。
- 发布时间：2026-08-17；AIHOT 分类：论文与研究。
- AIHOT 标签：
- AIHOT 判断：它把像素空间扩散模型的训练拆成先潜空间后像素空间过渡，并定位影响加速倍数的关键设计，为低延迟图像生成提供了一条绕开从头训练的可行路径。
- AIHOT 评分：53；评分用于站内排序，不等同于独立评测结论。
TopoReduce 编辑观察
当 AI 动态进入真实生产环境，团队需要同时关注能力边界、数据来源、调用成本、权限控制和可回滚性。把单条新闻放回完整工程链路中阅读，比只看标题更有助于判断它是否适合自己的产品和工作流。