EditMGT applies masked generative transformers with attention consolidation and region-hold sampling to deliver state-of-the-art localized image editing at 6x the speed of diffusion methods.
hub Mixed citations
OmniGen2: Towards Instruction-Aligned Multimodal Generation
Mixed citation behavior. Most common role is background (43%).
90
Pith papers citing it
Background
43% of classified citations
abstract
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2
hub tools
citation-role summary
background 17
baseline 15
other 2
dataset 1
citation-polarity summary
claims ledger
- abstract In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of Omn
co-cited works
representative citing papers
PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
MetaPoint represents 2D coordinates as special tokens in visual generative models to enable precise spatial control using existing positional encodings without architectural modifications.
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
Orthogonal Negative Guidance subtracts only the orthogonal component of negative-prompt attention features from positive ones in FLUX models to suppress concepts while preserving semantics and quality.
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiBench benchmark.
MetaEarth-MM unifies multi-modal remote sensing image generation and any-to-any translation across five modalities via scene-centered joint modeling on the new EarthMM dataset.
Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
Edit-Compass and EditReward-Compass are new unified benchmarks for fine-grained image editing evaluation and realistic reward modeling in reinforcement learning optimization.
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
UniPath adaptively models coordination-path diversity in unified multimodal models by training a path-conditioned executor and using a lightweight planner for input-dependent selection, improving performance over fixed strategies.
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
MULTITEXTEDIT benchmark reveals that all tested text-in-image editing models show pronounced degradation on non-English languages, especially Hebrew and Arabic, mainly in text accuracy and script fidelity.
XTC-Bench reveals that strong performance on generation or understanding tasks in unified multimodal models does not guarantee cross-task semantic consistency, which instead depends on how tightly coupled the learning objectives are across modalities.
A co-trained adapter framework enables mask-free local editing in DiTs by factorizing edit semantics from spatial location and jointly learning a mask predictor.
Fine-tuning multimodal models on a new synthetic spatial benchmark improves generative spatial compliance on real and synthetic tasks and transfers to better spatial understanding.
HP-Edit introduces a post-training framework and RealPref-50K dataset that uses a VLM-based HP-Scorer to align diffusion image editing models with human preferences, improving outputs on Qwen-Image-Edit-2509.
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.
ProVoice-Bench is the first framework to evaluate proactive voice agents, revealing that state-of-the-art multimodal LLMs struggle with over-triggering and context-aware reasoning.
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
citing papers explorer
-
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Meta-CoT uses two-level decomposition of editing operations into meta-tasks and a CoT consistency reward to improve granularity and generalization, reporting 15.8% gains across 21 tasks.
-
Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
-
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
DreamShot uses video diffusion priors and a role-attention consistency loss to produce coherent, personalized storyboards with better character and scene continuity than text-to-image methods.
-
Nucleus-Image: Sparse MoE for Image Generation
A 17B-parameter sparse MoE diffusion transformer activates 2B parameters per pass and reaches competitive quality on image generation benchmarks without post-training.
-
InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
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.
-
HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes
HorizonWeaver enables photorealistic, instruction-driven multi-level editing of complex driving scenes with improved generalization via a new paired dataset, language-guided masks, and joint training losses.
-
EmoCtrl: Controllable Emotional Image Content Generation
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
Adversarial Concept Distillation for One-Step Diffusion Personalization
OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.
-
Bridging Video Understanding and Generation in a Unified Framework
Vega unifies video understanding and generation via shared vocabulary and hybrid autoregressive-diffusion architecture, reporting strong results on VBench and VideoMME.
-
MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching
MT-EditFlow applies flow-matching RL with multi-reward aggregation to improve multi-turn image editing performance on models like FLUX.1-Kontext-dev by 6.85 points at turn-3.
-
GEM: Generative Supervision Helps Embodied Intelligence
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
-
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
GenEvolve introduces a self-evolving agent framework for image generation using tool-orchestrated trajectories and Visual Experience Distillation to achieve claimed SOTA results on benchmarks.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
InsHuman: Towards Natural and Identity-Preserving Human Insertion
InsHuman proposes Human-Background Adaptive Fusion, Face-to-Face ID-Preserving, and Bidirectional Data Pairing to enable natural human insertion in images without altering identity.
-
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
-
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
SmartPhotoCrafter performs automatic photographic image editing by coupling an Image Critic module that identifies deficiencies with a Photographic Artist module that generates edits, trained via multi-stage pretraining, reasoning supervision, and reinforcement learning.
-
UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement
UniCSG adds staged semantic disentanglement and frequency-aware reconstruction to DiT diffusion models to improve content preservation and style fidelity in both text- and reference-guided generation.
-
FineEdit: Fine-Grained Image Edit with Bounding Box Guidance
FineEdit adds multi-level bounding box injection to diffusion image editing, releases a 1.2M-pair dataset with box annotations, and shows better instruction following and background consistency than prior open models on new and existing benchmarks.
-
LongCat-Image Technical Report
LongCat-Image delivers a compact 6B-parameter bilingual image generation model that sets new standards for Chinese character rendering accuracy and photorealism while remaining efficient and fully open-source.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
Qwen-Image Technical Report
Qwen-Image is a foundation model that reaches state-of-the-art results in image generation and editing by combining a large-scale text-focused data pipeline with curriculum learning and dual semantic-reconstructive encoding for editing consistency.
-
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
ILLUME-X is a unified multimodal model that generates free-form interleaved text-image sequences via an expanded data pipeline, progressive self-adaptive training, and ILScore evaluation, claiming outperformance over prior unified models on style transfer, image decomposition, and storytelling.
-
UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization
UniVerse proposes a unified modulation framework for segmentation-free, disentangled multi-concept personalization in diffusion transformers, claiming superior localization and fidelity over baselines.
-
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
MMCORE transfers VLM reasoning into diffusion-based image generation and editing via aligned latent embeddings from learnable queries, outperforming baselines on text-to-image and editing tasks.
-
OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
-
Show-o2: Improved Native Unified Multimodal Models
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.
- UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
- Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer