WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
hub
PixelDiT: Pixel Diffusion Transformers for Image Generation
24 Pith papers cite this work. Polarity classification is still indexing.
24
Pith papers citing it
abstract
Latent-space modeling has been the standard for Diffusion Transformers (DiTs). However, it relies on a two-stage pipeline where the pretrained autoencoder introduces lossy reconstruction, leading to error accumulation while hindering joint optimization. To address these issues, we propose PixelDiT, a single-stage, end-to-end model that eliminates the need for the autoencoder and learns the diffusion process directly in the pixel space. PixelDiT adopts a fully transformer-based architecture shaped by a dual-level design: a patch-level DiT that captures global semantics and a pixel-level DiT that refines texture details, enabling efficient training of a pixel-space diffusion model while preserving fine details. PixelDiT achieves 1.61 FID on ImageNet 256 and 1.81 FID on ImageNet 512, surpassing existing pixel generative models. We further extend PixelDiT to text-to-image generation and pretrain it at the 10242resolution in pixel space. It achieves 0.74 on GenEval and 83.5 on DPG-bench, approaching the best latent diffusion models. Code: https://github.com/NVlabs/PixelDiT
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
years
2026 24representative citing papers
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
Cast3 translates NWP principles into a data-driven model using cubed-sphere grids, super-ensembles, and generative nudging to achieve state-of-the-art ensemble predictions that outperform baselines.
A single pixel-space diffusion model jointly performs 3D scene reconstruction and generation by supervising flow matching on rendered multi-view images, matching SOTA reconstruction and outperforming latent-space generation.
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
ViPSy constructs policy-aligned and visually grounded preference pairs for VLMs via visual cues from image variants, yielding SOTA hallucination reductions of 35.7% on AMBER and 24.5% on Object HalBench.
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.
CrossFlow is a cross-space flow model that generates pixels from noisy latents in one step, achieving 1.62 FID on class-conditional ImageNet-1k 256x256.
BareWave develops a waveform-native flow-matching framework for direct text-to-waveform TTS using representation alignment, staged noise scheduling, and velocity-aware perceptual alignment to achieve strong zero-shot voice cloning results.
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
A pixel-space network that injects frozen DINOv3 semantic features through spatially continuous per-pixel modulation reports state-of-the-art PSNR/SSIM/LPIPS on LOLv2-Real (29.08/0.902/0.089) and the best average across four paired LLIE benchmarks.
A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.
L2P repurposes pre-trained LDMs for direct pixel generation via large-patch tokenization and shallow-layer training on synthetic data, matching source performance with 8-GPU training and enabling native 4K output.
BitLM replaces per-token softmax with bitwise continuous diffusion inside causal blocks to generate multiple tokens in parallel while preserving autoregressive structure.
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
PixelGen augments pixel diffusion with gated perceptual supervision to reach FID 5.11 on ImageNet-256 and GenEval 0.79 in text-to-image, narrowing the gap to latent methods without VAEs.
FrequencyBooster reports state-of-the-art FID scores of 1.60 at 256x256 and 1.69 at 512x512 for pixel diffusion by using a specialized decoder for full-frequency modeling.
Register tokens improve pixel-space Diffusion Transformers by cleaning high-noise feature maps, and Register Guidance amplifies that effect.
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
CaloArt achieves top FPD, high-level, and classifier metrics on CaloChallenge datasets 2 and 3 while keeping single-GPU generation at 9-11 ms per shower by combining large-patch tokenization, x-prediction, and conditional flow matching.
FREPix generates images by transporting low- and high-frequency wavelet components along separate schedules, reaching 1.91 FID on ImageNet 256×256.
HyperDiT reports FID 1.56 on ImageNet 256x256 using hyper-connected cross-scale attention, SA-RoPE, and VFM registers in pixel space.
citing papers explorer
-
WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
WavTTS is the first raw-waveform diffusion TTS model using DiT flow matching and multi-scale mel supervision that approaches SOTA latent zero-shot performance while beating prior end-to-end models.
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
Cast3: Translating numerical weather prediction principles into data-driven forecasting
Cast3 translates NWP principles into a data-driven model using cubed-sphere grids, super-ensembles, and generative nudging to achieve state-of-the-art ensemble predictions that outperform baselines.
-
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
A single pixel-space diffusion model jointly performs 3D scene reconstruction and generation by supervising flow matching on rendered multi-view images, matching SOTA reconstruction and outperforming latent-space generation.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
PixGS is a single-stage pixel-space diffusion model that directly produces high-quality 3D Gaussian Splats from text or images in ~1s, outperforming multi-stage latent methods on standard benchmarks.
-
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
PixelU is a minimalist U-shaped Diffusion Transformer for pixel-space diffusion that decouples frequencies with zero-cost skip connections and constant-channel downsampling, outperforming baselines like JiT-G at 1/3 the compute cost with FID 1.63 on ImageNet 256x256.
-
Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs
ViPSy constructs policy-aligned and visually grounded preference pairs for VLMs via visual cues from image variants, yielding SOTA hallucination reductions of 35.7% on AMBER and 24.5% on Object HalBench.
-
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.
-
CrossFlow: One-Step Generation Across Latent and Pixel Spaces
CrossFlow is a cross-space flow model that generates pixels from noisy latents in one step, achieving 1.62 FID on class-conditional ImageNet-1k 256x256.
-
BareWave: Waveform-Native Flow-Matching Text-to-Speech
BareWave develops a waveform-native flow-matching framework for direct text-to-waveform TTS using representation alignment, staged noise scheduling, and velocity-aware perceptual alignment to achieve strong zero-shot voice cloning results.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
PixIE: Prompted Pixel-Space Low-Light Image Enhancement
A pixel-space network that injects frozen DINOv3 semantic features through spatially continuous per-pixel modulation reports state-of-the-art PSNR/SSIM/LPIPS on LOLv2-Real (29.08/0.902/0.089) and the best average across four paired LLIE benchmarks.
-
RiT: Vanilla Diffusion Transformers Suffice in Representation Space
A vanilla Diffusion Transformer trained via x-prediction on frozen DINOv2 features reaches FID 1.14 on ImageNet 256x256 with fewer parameters and faster sampling than prior DiT variants.
-
L2P: Unlocking Latent Potential for Pixel Generation
L2P repurposes pre-trained LDMs for direct pixel generation via large-patch tokenization and shallow-layer training on synthetic data, matching source performance with 8-GPU training and enabling native 4K output.
-
BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
BitLM replaces per-token softmax with bitwise continuous diffusion inside causal blocks to generate multiple tokens in parallel while preserving autoregressive structure.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
PixelGen: Improving Pixel Diffusion with Perceptual Supervision
PixelGen augments pixel diffusion with gated perceptual supervision to reach FID 5.11 on ImageNet-256 and GenEval 0.79 in text-to-image, narrowing the gap to latent methods without VAEs.
-
FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusion
FrequencyBooster reports state-of-the-art FID scores of 1.60 at 256x256 and 1.69 at 512x512 for pixel diffusion by using a specialized decoder for full-frequency modeling.
-
Registers Matter for Pixel-Space Diffusion Transformers
Register tokens improve pixel-space Diffusion Transformers by cleaning high-noise feature maps, and Register Guidance amplifies that effect.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
CaloArt: Large-Patch x-Prediction Diffusion Transformers for High-Granularity Calorimeter Shower Generation
CaloArt achieves top FPD, high-level, and classifier metrics on CaloChallenge datasets 2 and 3 while keeping single-GPU generation at 9-11 ms per shower by combining large-patch tokenization, x-prediction, and conditional flow matching.
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix generates images by transporting low- and high-frequency wavelet components along separate schedules, reaching 1.91 FID on ImageNet 256×256.
-
HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
HyperDiT reports FID 1.56 on ImageNet 256x256 using hyper-connected cross-scale attention, SA-RoPE, and VFM registers in pixel space.
- UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement