REVIEW 51 cited by
PixelFlow: Pixel-Space Generative Models with Flow
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
PixelFlow: Pixel-Space Generative Models with Flow
read the original abstract
We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow.
Forward citations
Cited by 51 Pith papers
-
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.
-
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
Training a small adapter on a frozen pixel diffusion model's own samples and extrapolating the final prediction away from the adapter's intermediate prediction improves FID on ImageNet.
-
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA ...
-
Asymmetric Flow Models
Asymmetric Flow Modeling restricts noise prediction to a low-rank subspace for high-dimensional flow generation, reaching 1.57 FID on ImageNet 256x256 and new state-of-the-art pixel text-to-image performance via finet...
-
Asymmetric Flow Models
AsymFlow uses rank-asymmetric velocity prediction to reach 1.57 FID on ImageNet 256x256 and enables finetuning of latent flow models into superior pixel-space text-to-image generators.
-
Coevolving Representations in Joint Image-Feature Diffusion
CoReDi coevolves semantic representations with the diffusion model via a jointly learned linear projection stabilized by stop-gradient, normalization, and regularization, yielding faster convergence and higher sample ...
-
Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction
Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives tha...
-
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Representation Forcing lets a UMM decoder autoregressively predict its own understanding representations as in-context tokens that guide pixel-space diffusion, matching VAE-based generation without an external latent space.
-
WaiT for the Signal: Simple Frequency-Aware Flow-Matching
WaiT delays high-frequency wavelet bands in flow-matching image generation until coarse structure emerges, improving quality and cutting compute, with a reported SOTA FID of 1.30 on ImageNet 512.
-
Twins: Learn to Predict Unified Representations with Focal Loss
Channel-wise concatenation of SigLIP2 and Flux VAE features into one token, trained with a focal-style flow-matching loss, yields a unified representation with 1.59 gFID on ImageNet 256 and VAE-level reconstruction.
-
DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer
DuSPiT splits pixel diffusion into a compact global-structure branch and a high-capacity subpatch detail branch, reaching ImageNet-512 FID 1.52 at 329 GFLOPs, below JiT-G/32 (1.78).
-
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.
-
PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation
A single-stage pixel-space diffusion model for direct 3D Gaussian Splat generation that bypasses latent compression and adds geometric supervisions to outperform prior multi-stage methods.
-
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 t...
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
MIMFlow is an end-to-end model that routes semantic latents through a normalizing flow while a decoder handles high-frequency pixels, reporting FID 2.50 and 71.3% linear probing accuracy on ImageNet 256x256 with 128 tokens.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
MIMFlow uses a VAE on masked images to feed semantic latents to a normalizing flow while a decoder handles high-frequency details, reporting FID 2.50 and 71.3% linear probing on ImageNet 256x256 with 128 tokens.
-
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
End-to-end masked-image VAE plus normalizing flow yields FID 2.50 on ImageNet 256 with 128 tokens and higher linear-probe accuracy than unmasked counterparts.
-
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Representation Forcing enables end-to-end pixel-space unified multimodal models by making visual representation prediction a native autoregressive generation target that guides subsequent pixel diffusion in the same backbone.
-
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
MIND integrates discrete patch tokenization into diffusion score functions via soft top-k and dual-branch layers, achieving FID 22.73 (no guidance) and 2.06 (with guidance) on ImageNet-256 after 80 epochs, outperformi...
-
Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry
MIND integrates discrete patch tokenization into diffusion score functions via soft top-k aggregation and dual-branch embeddings, achieving FID 1.95 on ImageNet-256 with 715M parameters while outperforming larger 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 acro...
-
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.
-
WavFlow: Audio Generation in Waveform Space
WavFlow performs direct waveform audio generation via flow matching on 2D token grids from raw patches plus amplitude lifting, matching latent-based methods on VGGSound and AudioCaps without intermediate compression.
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
SRC-Flow compresses RAE features into a low-dimensional semantic space with a Semantic Representation Compressor, enabling normalizing flows to achieve SOTA gFID scores of 1.65 and 2.07 on ImageNet 256x256 and 512x512...
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
SRC-Flow compresses RAE features via a Semantic Representation Compressor into a low-dimensional space, enabling normalizing flows to reach gFID 1.65 on ImageNet 256x256 and 2.07 on 512x512 while retaining exact likelihoods.
-
SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation
A learned 32-channel semantic compression lets a normalizing flow reach gFID 1.65 on ImageNet 256×256, the best FID reported for flow-based image generation.
-
HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
HyperDiT achieves FID 1.56 on ImageNet 256x256 in pixel space via hyper-connected cross-scale interactions, cross-attention, SA-RoPE, and VFM registers.
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
-
A Few-Step Generative Model on Cumulative Flow Maps
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
-
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.
-
MotionHiFlow: Text-to-motion via hierarchical flow matching
MotionHiFlow generates text-aligned 3D human motions using hierarchical flow matching across temporal scales, cross-scale transitions, a Text-Motion Diffusion Transformer, and a topology-aware Motion VAE, achieving st...
-
Continuous Adversarial Flow Models
Continuous adversarial flow models replace MSE in flow matching with adversarial training via a discriminator, improving guidance-free FID on ImageNet from 8.26 to 3.63 for SiT and similar gains for JiT and text-to-im...
-
Cross-Resolution Distribution Matching for Diffusion Distillation
Cross-resolution distribution matching with logSNR timestep alignment and predicted-noise re-injection enables high-fidelity few-step multi-resolution cascaded diffusion distillation.
-
Protein Autoregressive Modeling via Multiscale Structure Generation
PAR is a multi-scale autoregressive transformer framework for protein backbone generation that uses coarse-to-fine prediction, noisy context learning, and flow-based decoding to achieve high-quality unconditional and ...
-
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
LLSA uses hierarchical top-K selection plus coarse-token enrichment to make diffusion-transformer attention O(N log N), giving about 6x faster training at 256x256 pixel resolution with FID comparable to full attention.
-
PixelDiT: Pixel Diffusion Transformers for Image Generation
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
-
SURF: Signature-Retained Fast Video Generation
SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while clos...
-
Back to Basics: Let Denoising Generative Models Denoise
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
-
STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching
A hybrid stereo-matching model uses a cascade matching network to propose disparities and a diffusion transformer to refine ambiguous regions; it claims state-of-the-art benchmark results.
-
Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold
x-prediction maintains manifold adherence during training-free diffusion guidance better than ε- or v-prediction, per theoretical analysis and experiments on bird classification and style transfer.
-
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Trajectory Forcing makes generative image synthesis trajectory-centric by organizing it into decodable semantic stages derived from clustered visual representations and trained with one-step flow-matching models.
-
PixIE: Prompted Pixel-Space Low-Light Image Enhancement
PixIE proposes a feed-forward pixel-space low-light image enhancement network using DINO-prompted pixel blocks, spatial-channel compaction, and multi-receptive-field embeddings, claiming 1.9-15.0% PSNR gains and 8.5-4...
-
PixIE: Prompted Pixel-Space Low-Light Image Enhancement
PixIE proposes a pixel-space low-light image enhancement framework using DINO-prompted blocks, spatial-channel compaction, and multi-receptive-field embeddings, reporting PSNR gains of 1.9-15.0% and LPIPS reductions o...
-
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.
-
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.
-
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.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.
-
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Training flow matching along sphere geodesics with a curvature-aware loss weight lets standard DiT-B converge on DINOv2 features (FID 3.37 with guidance), contradicting the need for width scaling.
-
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.
-
Pixel-Space Diffusion Transformers
A systematic review of pixel-space diffusion transformers, categorizing architectures and challenges for end-to-end image generation without latent compression.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.