Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
read the original abstract
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as [nextline] and [nextframe] tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. This unified approach enables training within a single framework for different modalities and allows for flexible generation of multimodal data at any resolution, aspect ratio, and length during inference. Advanced techniques like RoPE, RMSNorm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. We expect that the open-sourcing of Lumina-T2X will further foster creativity, transparency, and diversity in the generative AI community.
This paper has not been read by Pith yet.
Forward citations
Cited by 13 Pith papers
-
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
iTryOn is a diffusion-based framework that adds spatial 3D hand guidance and semantic action-aware embeddings to handle complex garment deformations during human-clothing interactions in videos.
-
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
iTryOn is a video diffusion Transformer that injects spatial 3D hand guidance and semantic action captions to enable interactive garment replacement in videos.
-
Your Pre-trained Diffusion Model Secretly Knows Restoration
Pre-trained diffusion models inherently support image restoration that can be unlocked by optimizing prompt embeddings at the text encoder output using a diffusion bridge formulation, achieving competitive results on ...
-
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
Introduces SciIR-82k dataset and SciIR-Bench for scientific image reasoning generation organized by Peirce's semiotic triad, with fine-tuning raising model score from 35% to 43%.
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
-
PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion
PAI-Studio reformulates cinematic background replacement as in-context conditional generation inside a Diffusion Transformer with bidirectional attention, trained on a new 30K film-sourced dataset, and reports better ...
-
Rethinking Cross-Layer Information Routing in Diffusion Transformers
DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.
-
Rethinking Cross-Layer Information Routing in Diffusion Transformers
DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.
-
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
PoM is a new linear-complexity token mixer using learned polynomials that matches attention performance in transformers while enabling efficient long-sequence processing.
-
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
UniCanvas introduces a diffusion-based approach for unified multimodal generation by embedding text as visual patterns within images on a shared canvas.
-
LTX-2: Efficient Joint Audio-Visual Foundation Model
LTX-2 generates high-quality synchronized audiovisual content from text prompts via an asymmetric 14B-video / 5B-audio dual-stream transformer with cross-attention and modality-aware guidance.
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and strea...
-
HunyuanVideo: A Systematic Framework For Large Video Generative Models
HunyuanVideo presents a 13B-parameter open-source video generative model with integrated data, architecture, training, and inference systems whose professional evaluations show it outperforming prior SOTA models inclu...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.