Introduction
Tencent shifts toward native multimodal image generation with open weights and stronger instruction understanding.
View full image ↗Generated-example collection from the official HunyuanImage 3.0 repository, preserving the original arrangement of published model outputs.
Tencent HunyuanImage research team · Rights in the original image and document remain with their respective holders
Source · GitHub - Tencent-Hunyuan/HunyuanImage-3.0: HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation · GitHub ↗RESEARCH ACCOUNT
Research documentation and runtime materials enter the public record together.
ANTI-AI ARCHIVE · Revised 2026-10-02
Release and use
The HunyuanImage 3.0 repository records its report, inference code and weights on 28 September 2025. Later acceleration support and the 2026 instruction version have their own dates. The maintained page is a changing record; later editing capabilities should not all be attributed to September’s version.
Section sources: HunyuanImage 3.0
Change in creative practice
Runtime materials allow a model to become an installable component of a creative workflow, but its combination with prompt processing and application interfaces still matters. Version records help trace that combination while distinguishing the report’s capability claims from observations of actual use.
Section sources: HunyuanImage 3.0
Sources for this account
Official release scope and demonstration descriptions read; vendor performance claims are not treated as independent test results.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and HunyuanImage 2.1.
Compare the methods, forms of control or presentation contexts of this entry and HunyuanImage 3.0 Instruct / Instruct-Distil.
Dates & version record
Date displayed for this node: 2025-09-28 · Historical date recorded for the source: 2025-09-28
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
HunyuanImage 3.0
https://github.com/Tencent-Hunyuan/HunyuanImage-3.0
Current cited URL
This is the archive’s bilingual research abstract. The external link is an original source, not a claim that the publisher offers full text in both languages.
Provenance, translation & verification
Timeline entry #308 · Open model
Research materials & supplement references · 1
GenAI Visual Release Chronology Research Master · p. 33 · R181
Date as recorded: 2025-09-28
HunyuanImage 3.0 ↗
HunyuanImage 3.0
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. HunyuanImage 3.0. Art-history node #308. https://salondesrefuses.cn/en/art-history/211
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.