The work creates the first dataset and baseline for generating emission textures on 3D objects to reproduce glowing materials from input images.
hub Mixed citations
HunyuanImage 3.0 Technical Report
Mixed citation behavior. Most common role is background (50%).
41
Pith papers citing it
Background
50% of classified citations
abstract
We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training, aggressive model post-training, and an efficient infrastructure that enables large-scale training and inference. With these advancements, we successfully trained a Mixture-of-Experts (MoE) model comprising over 80 billion parameters in total, with 13 billion parameters activated per token during inference, making it the largest and most powerful open-source image generative model to date. We conducted extensive experiments and the results of automatic and human evaluation of text-image alignment and visual quality demonstrate that HunyuanImage 3.0 rivals previous state-of-the-art models. By releasing the code and weights of HunyuanImage 3.0, we aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant multimodal ecosystem. All open source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanImage-3.0
hub tools
citation-role summary
background 7
baseline 6
method 1
citation-polarity summary
representative citing papers
Arena-T2I Hard benchmark with ~30 decomposed constraints per prompt and a dependency-aware checklist reward yields better faithfulness-aesthetics trade-off than single-reward or weighted-sum baselines on SD3.5-Medium and FLUX.1-dev.
JAVEdit-100k is the first large-scale dataset for instruction-guided joint audio-visual video editing, accompanied by JAVEditBench and the JAVEdit model that outperforms baselines on five of six metrics.
Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
Banana100 dataset shows that none of 21 popular NR-IQA metrics consistently rate images degraded by 100 iterative edits lower than clean originals.
Gen-Searcher is the first trained search-augmented image generation agent using SFT followed by GRPO reinforcement learning with dual text-image rewards, delivering 15-16 point gains on knowledge-intensive benchmarks.
GAR-Font is a global-aware autoregressive framework for multimodal few-shot font generation that adds global tokenization, a language-style adapter, and post-refinement to improve style coherence over patch-based methods.
AIA loss teaches unified multimodal models task-specific cross-modal attention patterns to reduce conflicts between image understanding and generation without architecture decoupling.
Fleet achieves dynamic few-shot adaptation for AIGI detection via avoidance routing in decoupled subspaces, raising accuracy from 20.4% to 73.1% on new generators like Doubao Seedream 4.0 with 10 shots.
Introduces FEPBench benchmark to evaluate T2I models on instruction faithfulness, reasoning enrichment, and semantic precision for natural-science illustrations using atom set annotations.
TextWand unifies scene text removal, generation and replacement via rendering/erasure decomposition, ORPE for layout fidelity, RAS for clean erasure, and the new TextWand-Bench dataset, claiming superior accuracy and quality over prior models.
Qwen-Image-Bench introduces a hierarchical creator-centric benchmark with 1000 prompts, 23 sub-capabilities, and a Q-Judger model that scores images on 56 verifiable facets to distinguish T2I models on fidelity and creativity.
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
SpecSem-Net integrates Fourier-based spectral filtering with semantic-guided gated merging to detect AI-generated videos, reporting 87.25% accuracy on a new benchmark of five commercial generators and 95.59% on public datasets.
CLVR framework adds closed-loop visual verification, proxy prompt reinforcement learning, and delta-space weight merge to improve complex text-to-image generation over single-step or unverified multi-step baselines.
Qwen-Image-VAE-2.0 achieves state-of-the-art high-compression image reconstruction and superior diffusability for diffusion models, with a new text-rich document benchmark.
D-OPSD formulates supervised fine-tuning of step-distilled diffusion models as on-policy self-distillation by having the model act as both teacher (with multimodal context) and student (with text-only context) on its own roll-outs.
Refinement via Regeneration (RvR) reformulates image refinement in unified multimodal models as conditional regeneration using prompt and semantic tokens from the initial image, yielding higher alignment scores than editing-based methods.
By requiring and using highly discriminative LLM text features, the work enables the first effective one-step text-conditioned image generation with MeanFlow.
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
IdGlow is a progressive two-stage diffusion framework that uses task-adaptive timestep scheduling, temporal gating, VLM prompt synthesis, and group-level DPO to balance identity preservation and scene coherence in multi-subject image generation.
HunyuanVideo 1.5 delivers state-of-the-art open-source text-to-video and image-to-video generation with an 8.3B parameter DiT model featuring SSTA attention, glyph-aware encoding, and progressive training.
PaintBench provides a scalable deterministic benchmark for precise visual editing operations, revealing that even the best of 11 models achieves only 17.1% mIoU and that scores correlate strongly with applied data visualization editing performance.
citing papers explorer
-
Qwen-Image-2.0 Technical Report
Qwen-Image-2.0 unifies high-fidelity image generation and precise editing by coupling Qwen3-VL with a Multimodal Diffusion Transformer, improving text rendering, photorealism, and complex prompt following over prior versions.