SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens
Recent unified models such as Bagel demonstrate that paired image-edit data can effectively align multiple visual tasks within a single diffusion transformer. However, these models remain limited to single-condition inputs and lack the flexibility needed to synthesize results from multiple heterogeneous sources. We present SIGMA (Selective-Interleaved Generation with Multi-Attribute Tokens), a unified post-training framework that enables interleaved multi-condition generation within diffusion transformers. SIGMA introduces selective multi-attribute tokens, including style, content, subject, and identity tokens, which allow the model to interpret and compose multiple visual conditions in an interleaved text-image sequence. Through post-training on the Bagel unified backbone with 700K interleaved examples, SIGMA supports compositional editing, selective attribute transfer, and fine-grained multimodal alignment. Extensive experiments show that SIGMA improves controllability, cross-condition consistency, and visual quality across diverse editing and generation tasks, with substantial gains over Bagel on compositional tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
Interleaved reasoning paradigms enhance Multimodal Large Language Models (MLLMs) with visual feedback but are hindered by the prohibitive computational cost of re-encoding pixel-dense images. A promising alternative, lat…
Multimodal ReasoningVisual ReasoningDraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limite…
Text-to-Image GenerationMultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model produc…
Image GenerationLateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations
Recent advancements in Vision-Language Models (VLMs) have led to the development of Vision-Language Generalists (VLGs) capable of understanding and generating interleaved images and text. Despite these advances, VLGs sti…
AttributeImage GenerationVINO: A Unified Visual Generator with Interleaved OmniModal Context
We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independent modules for each modality, VINO uses a…
Instruction FollowingVideo Generation