REVIEW 30 cited by
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
read the original abstract
Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.
Forward citations
Cited by 30 Pith papers
-
Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset
A new 100k triplet dataset and in-context diffusion framework ICTone enable state-of-the-art tone style transfer by jointly conditioning on content and reference images with scorer-based reward learning.
-
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
-
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
DSH-Bench is a benchmark for subject-driven T2I generation that uses hierarchical taxonomy sampling, difficulty/scenario classification, and a new SICS metric showing 9.4% higher human correlation than prior measures.
-
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
InstructMoLE replaces per-token routing with instruction-guided global routing for mixture-of-low-rank-experts in diffusion transformers and adds an output-space orthogonality loss to improve multi-conditional image g...
-
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.
-
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
DSH-Bench supplies a hierarchical 58-category subject set, difficulty/scenario labels, and a human-aligned SICS metric that exposes systematic failures of 19 subject-driven T2I models.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
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 keepin...
-
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.
-
Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition
Fashion130K dataset and UMC framework align text and visual prompts with embedding refiner, Fusion Transformer, and redesigned attention to generate more consistent outfits than prior methods.
-
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Vanast produces coherent garment-transferred human animation videos from a single human image, garment images, and pose guidance video using synthetic triplet supervision and a Dual Module video diffusion transformer ...
-
Hierarchical Concept-to-Appearance Guidance for Multi-Subject Image Generation
A diffusion-transformer framework with VLM-grounded masked attention and VAE dropout improves identity and prompt fidelity for multi-subject image generation.
-
Muses: Designing, Composing, Generating Nonexistent Fantasy 3D Creatures without Training
Muses creates new fantasy 3D animals by designing a combined skeleton, fusing voxel parts from separate 3D models along that skeleton, then restyling textures via image editing — with no training.
-
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
-
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Scone adds a semantic-bridge attention-masking step to a unified understanding-generation model, improving subject distinction in multi-candidate reference images, and introduces the SconeEval benchmark.
-
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation
iMontage repurposes a pretrained video diffusion model to generate coherent yet highly dynamic image sets from arbitrary numbers of input images.
-
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 fo...
-
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.
-
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
A reinforcement-learning reward based on bipartite face matching improves multi-identity consistency and reduces identity confusion in image customization models.
-
FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
FocusDPO adds dynamic spatial weighting to preference-based fine-tuning, improving subject fidelity and reducing attribute leakage in multi-subject personalized image generation.
-
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
USO trains one DiT model for subject-driven, style-driven, and joint generation by disentangling content and style from triplet data and adding a style-reward objective, claiming SOTA on USO-Bench.
-
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
FreeGraftor performs subject-driven text-to-image generation without training by cross-image feature grafting via semantic matching, position-constrained attention fusion, and a noise initialization strategy that pres...
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance introduces a dual-stream MoE model with modality-aware rotary positional encoding and staged multi-task training that outperforms open-source unified models on image and video generation while retaining understa...
-
ID-Sim: An Identity-Focused Similarity Metric
ID-Sim is a new similarity metric that aims to capture human selective sensitivity to identities by training on curated real and generative synthetic data and validating against human annotations on recognition, retri...
-
PureCC: Pure Learning for Text-to-Image Concept Customization
PureCC introduces a decoupled learning objective, dual-branch training pipeline with frozen extractor, and adaptive guidance scale λ* for high-fidelity concept customization while preserving original model behavior in...
-
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.
-
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 consis...
-
RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation
RAVA retrieves view-consistent target-subject images via a learned cross-instance embedding and LogDet subset selection, then uses them in a multi-reference generator to improve cross-subject viewpoint alignment.
-
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.
-
EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation
EditIDv2 fine-tunes only PerceiverAttention cross-attention weights on 3K images to inject editability into Flux-based ID customization, reporting selective gains on the self-proposed IBench benchmark.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.