No article text was recorded for this version.
text-to-image scalability
Version 2 of 2134 papers134 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Multi-Architecture Multi-Expert Diffusion Models
- Blog: SF-V: Single Forward Video Generation Model
- Blog: A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning
- Blog: Stochastic Interpolants via Conditional Dependent Coupling
- Blog: Latent Diffusion Model without Variational Autoencoder
- Blog: UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
- Blog: Diffusion Transformers with Representation Autoencoders
- Blog: Exploring Diffusion Time-steps for Unsupervised Representation Learning
- Blog: Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
- Blog: SPIRE: Conditional Personalization for Federated Diffusion Generative Models
- Blog: IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction
- Blog: FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation
- Blog: Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
- Blog: MaskBit: Embedding-free Image Generation via Bit Tokens
- Blog: No Alignment Needed for Generation: Learning Linearly Separable Representations in Diffusion Models
- Blog: Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
- Blog: One-step Latent-free Image Generation with Pixel Mean Flows
- Blog: GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis
- Blog: Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
- Blog: There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-Training
- Blog: EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
- Blog: SoFlow: Solution Flow Models for One-Step Generative Modeling
- Blog: Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
- Blog: Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
- Blog: Dual-Path Condition Alignment for Diffusion Transformers
- Blog: Autoregressive Image Generation with Masked Bit Modeling
- Blog: ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model
- Blog: Diverse Image Style Transfer via Invertible Cross-Space Mapping
- Blog: Classification-Denoising Networks
- Blog: Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
- Blog: Denoising MCMC for Accelerating Diffusion-Based Generative Models
- Blog: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
- Blog: reAR: Rethinking Visual Autoregressive Models via Token-wise Consistency Regularization
- Blog: RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
- Blog: Language Model Beats Diffusion - Tokenizer is key to visual generation
- Blog: MCGAN: Enhancing GAN Training with Regression-Based Generator Loss
- Blog: Diverse Image Inpainting with Bidirectional and Autoregressive Transformers
- Blog: TinyFusion: Diffusion Transformers Learned Shallow
- Blog: NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs
- Blog: Learning Modulated Transformation in GANs
- Blog: End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
- Blog: Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models
- Blog: Diffusion Models with Deterministic Normalizing Flow Priors
- Blog: Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
- Blog: Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
- Blog: Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
- Blog: Slimmable Generative Adversarial Networks
- Blog: SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer
- Blog: M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
- Blog: DiP: Taming Diffusion Models in Pixel Space
- Blog: Diffusion Models with Deterministic Normalizing Flow Priors
- Blog: DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
- Blog: Semantic-guided LoRA Parameters Generation
- Blog: FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
- Blog: Masked Diffusion Transformer is a Strong Image Synthesizer
- Blog: Image Generation Diversity Issues and How to Tame Them
- Blog: How to Synthesize Text Data without Model Collapse?
- Blog: Diffusion Models without Classifier-free Guidance
- Blog: Scalable Diffusion Models with Transformers
- Blog: HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation
Showing 60 of 134 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_text_to_image_scalability_ddb6b4af,
title = {text-to-image scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/text-to-image-scalability/rdr_ddb6b4af809c48abb543a964664bb970},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_text_to_image_scalability_ddb6b4af_v2,
title = {text-to-image scalability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/text-to-image-scalability/rdr_ddb6b4af809c48abb543a964664bb970/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}