| SenseNova-U1.5: Towards Native Unified Visual Intelligence | ✓ Link | 0.948 | 0.978 | SenseNova-U1.5-8B-MoT | 2026-09-10 |
| SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture | ✓ Link | 0.940 | 0.972 | SenseNova-U1-8B-MoT | 2026-05-12 |
| HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer | ✓ Link | 0.9222 | 0.9628 | HiDream-O1-Image-Pro | 2026-05-11 |
| HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer | ✓ Link | 0.9128 | 0.9561 | HiDream-O1-Image | 2026-05-11 |
| Emu3.5: Native Multimodal Models are World Learners | ✓ Link | 0.9123 | | Emu3.5 (34B) | 2025-10-30 |
| GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation | ✓ Link | 0.9116 | | GLM-Image | 2026-01-14 |
| Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models | ✓ Link | 0.889 | 0.965 | Lens-Turbo | 2026-05-20 |
| Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing | ✓ Link | 0.887 | 0.950 | Mage-Flow | 2026-07-21 |
| LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes | ✓ Link | 0.875 | 0.945 | LLaDA-Image | 2026-09-03 |
| Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation | ✓ Link | 0.8739 | 0.9369 | JoyAI-Image | 2026-05-05 |
| Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer | ✓ Link | 0.8671 | 0.9367 | Z-Image | 2025-11-27 |
| LongCat-Image Technical Report | ✓ Link | 0.8658 | 0.9361 | LongCat-Image | 2025-12-08 |
| i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models | ✓ Link | 0.8531 | | i1 | 2026-06-09 |
| Qwen-Image Technical Report | ✓ Link | 0.8288 | 0.9116 | Qwen-Image | 2025-08-04 |
| APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation | ✓ Link | 0.821 | | LongCat-Image (w/ APT) | 2026-10-13 |
| S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation | ✓ Link | 0.8039 | | S1-Omni | 2026-07-17 |
| VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation | ✓ Link | 0.7841 | 0.9081 | NextFlow-RL | 2026-01-05 |
| DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing | ✓ Link | 0.7533 | 0.8936 | DeepGen-1.0 (RL) | 2026-02-12 |
| InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing | ✓ Link | 0.623 | | InternVL-U (4B) | 2026-03-10 |
| Ovis-Image Technical Report | ✓ Link | | 0.9695 | Ovis-Image (2B+7B) | 2025-11-28 |