GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
hub Mixed citations
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Mixed citation behavior. Most common role is background (55%).
42
Pith papers citing it
1
external citations · Pith
Background
55% of classified citations
abstract
We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT
hub tools
citation-role summary
background 6
baseline 4
dataset 1
citation-polarity summary
representative citing papers
PULSE collocates skip-connected encoder-decoder layers and uses a skip-aware DP partitioner plus ILP scheduler to reduce communication 89% and raise throughput up to 2.3x versus prior pipeline strategies for diffusion models.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
AsymFlow uses rank-asymmetric velocity prediction to reach 1.57 FID on ImageNet 256x256 and enables finetuning of latent flow models into superior pixel-space text-to-image generators.
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
TivTok factorizes video clips into reusable time-invariant tokens and frame-specific time-variant tokens via Scope-Induced Factorization and Invariant Broadcasting, achieving 2.91x better compression for 128-frame videos on benchmarks.
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
AI-T2I improves text-to-image alignment in diffusion models by using aggregation and isolation losses on cross-attention maps to fix scattering and overlap issues.
ABSS ranks diffusion seeds by early cross-attention strength to prompt core tokens and retains only the top-k for full generation, yielding consistent gains in alignment and quality on Stable Diffusion variants.
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.
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.
Fashion130K dataset and UMC framework align text and visual prompts to generate more consistent fashion outfits than prior state-of-the-art methods.
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
L2P trains per-timestep linear weights on feature trajectories in about 20 seconds to enable aggressive caching in DiT models, delivering up to 4.55x FLOPs reduction with maintained visual quality.
CineAGI is a multi-agent LLM framework that generates multi-scene movies with improved character consistency, narrative coherence, and audio-visual alignment.
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.
LAION-Aesthetics Predictor reinforces Western and male biases by preferentially selecting images associated with women and realistic Western/Japanese art while excluding men, LGBTQ+ references, and other styles.
A 6B single-stream diffusion transformer trained with heavily curated data reaches top open-source image-generation quality in 314K H800 GPU hours, releasing Turbo and Edit variants.
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
citing papers explorer
-
GeoFidelity-Bench: Evaluating Segment-Level Geographic Fidelity in Text-to-Image Street-View Generation
GeoFidelity-Bench shows text-to-image models gain city-level plausibility from local names but achieve near-zero improvement in exact segment identity, with GPS coordinates adding no benefit.
-
Pulse: Training Acceleration for Large Diffusion Models with Automatic Pipeline Parallelism
PULSE collocates skip-connected encoder-decoder layers and uses a skip-aware DP partitioner plus ILP scheduler to reduce communication 89% and raise throughput up to 2.3x versus prior pipeline strategies for diffusion models.
-
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
-
Asymmetric Flow Models
AsymFlow uses rank-asymmetric velocity prediction to reach 1.57 FID on ImageNet 256x256 and enables finetuning of latent flow models into superior pixel-space text-to-image generators.
-
VACE: All-in-One Video Creation and Editing
VACE unifies reference-to-video generation, video-to-video editing, and masked video-to-video editing in one Diffusion Transformer framework using a Video Condition Unit for inputs and a Context Adapter for task injection.
-
TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization
TivTok factorizes video clips into reusable time-invariant tokens and frame-specific time-variant tokens via Scope-Induced Factorization and Invariant Broadcasting, achieving 2.91x better compression for 128-frame videos on benchmarks.
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
-
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
TunerDiT adds event-partitioned masking and cross-event prompt fusion to diffusion transformers for training-free multi-event video generation, with gains scaling by event count on a new Meve benchmark.
-
AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
AI-T2I improves text-to-image alignment in diffusion models by using aggregation and isolation losses on cross-attention maps to fix scattering and overlap issues.
-
Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
ABSS ranks diffusion seeds by early cross-attention strength to prompt core tokens and retains only the top-k for full generation, yielding consistent gains in alignment and quality on Stable Diffusion variants.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
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.
-
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
-
ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
-
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.
-
Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
Fashion130K dataset and UMC framework align text and visual prompts to generate more consistent fashion outfits than prior state-of-the-art methods.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
L2P trains per-timestep linear weights on feature trajectories in about 20 seconds to enable aggressive caching in DiT models, delivering up to 4.55x FLOPs reduction with maintained visual quality.
-
CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration
CineAGI is a multi-agent LLM framework that generates multi-scene movies with improved character consistency, narrative coherence, and audio-visual alignment.
-
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.
-
The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor
LAION-Aesthetics Predictor reinforces Western and male biases by preferentially selecting images associated with women and realistic Western/Japanese art while excluding men, LGBTQ+ references, and other styles.
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
A 6B single-stream diffusion transformer trained with heavily curated data reaches top open-source image-generation quality in 314K H800 GPU hours, releasing Turbo and Edit variants.
-
PixelDiT: Pixel Diffusion Transformers for Image Generation
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
-
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
UniWorld-V2 applies policy optimization via DiffusionNFT and MLLM logit feedback with group filtering to reach state-of-the-art scores of 4.49 on ImgEdit and 7.83 on GEdit-Bench while remaining model-agnostic.
-
HunyuanImage 3.0 Technical Report
HunyuanImage 3.0 is an open 80B-parameter multimodal autoregressive image generator that reportedly matches leading closed models on in-house benchmarks.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
-
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Seedream 2.0 is a native Chinese-English bilingual diffusion model that integrates a self-developed LLM text encoder, Glyph-Aligned ByT5, and Scaled ROPE to reach claimed state-of-the-art results in prompt following, aesthetics, text rendering, and human preference alignment via RLHF.
-
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
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.
-
MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
MONET is an open 104.9M image-text pair dataset created via safety filtering, deduplication, and multi-VLM recaptioning from 2.9B raw pairs, validated by training a competitive 4B-parameter latent diffusion model.
-
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
WinTok is a hybrid visual tokenizer that supplements pixel tokens with learnable semantic tokens distilled asymmetrically from foundation models to improve reconstruction, understanding, and generation.
-
ACPO: Anchor-Constrained Perceptual Optimization for Diffusion Models with No-Reference Quality Guidance
ACPO uses anchor-based regularization with NR-IQA guidance to enable stable perceptual quality improvements in diffusion model fine-tuning.
-
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
Diffusion Templates is a unified plugin framework that allows injecting various controllable capabilities into diffusion models through a standardized interface.
-
OmniGen2: Towards Instruction-Aligned Multimodal Generation
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consistency among open-source models on the new OmniContext benchmark.
-
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.
-
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.
-
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.
-
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.
-
Open-Sora Plan: Open-Source Large Video Generation Model
Open-Sora Plan presents an open-source large video generation model that combines a Wavelet-Flow VAE, Joint Image-Video Skiparse Denoiser, and multi-dimensional data curation to achieve high-quality video outputs with public code and weights.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Scaling data, model size, and training optimization on the Janus architecture yields better multimodal understanding and more stable, instruction-following text-to-image generation.