HunyuanImage 3.0 Technical Report
Report on the HunyuanImage 3.0 multimodal model by the Tencent Hunyuan Foundation Model Team; cited at arXiv version 1 of 28 September 2025.
- Issued by
- Tencent / 腾讯
- Authors credited
- No authorship claim recorded yet. The source record lists Tencent Hunyuan Foundation Model Team.
- Dates
- Published 2025-09-28 issue evidence
- Exact source
- HunyuanImage 3.0 Technical Report arXiv · published 2025-09-28 · Dated document, retrieved on 2026-10-29 (SHA-256 aca2dbdfddd1df7d1ffe914c99242a0a402bc5cc1c9dc6bb34ced75699207361) directly from the publisher. Version: 2509.23951v1. Version 1 as submitted on 28 September 2025; versions 2 and 3 not inspected.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
- Issued by: Tencent / 腾讯Tencent's Hunyuan Foundation Model Team posted the HunyuanImage 3.0 technical report to arXiv on 28 September 2025 (version 1), describing a native multimodal model 'with its image generation module publicly available'.2025-09-28 · publication · Stated in source · Supported Inspect claim & evidence ↗Tencent / 腾讯: institution →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.