PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Paper
• 2310.00426 • Published
• 61
generative-model-training
-
-
A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation
Paper • 2310.16656 • Published • 53 -
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images
Paper • 2310.16825 • Published • 36 -
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers
Paper • 2401.11605 • Published • 23 -
GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering
Paper • 2402.10128 • Published • 17 -
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
Paper • 2409.04410 • Published • 25 -
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Paper • 2410.08261 • Published • 52 -
XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework
Paper • 2501.08809 • Published • 10 -
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
Paper • 2501.09019 • Published • 12 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8 -
Diffusion Models without Classifier-free Guidance
Paper • 2502.12154 • Published • 8 -
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Paper • 2504.16064 • Published • 14 -
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Paper • 2512.16905 • Published • 32