| FlowAR |
- FID
- 1.65
|
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching 2024-12-19 |
코드 1 |
| FACM (1-step) |
- FID
- 1.70
- NFE
- 1
|
Flow-Anchored Consistency Models 2025-07-04 |
코드 1 |
| DiT-XL/2 with CADS |
- FID
- 1.70
|
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling 2023-10-26 |
연결 없음 |
| DiMR-XL/2R |
- FID
- 1.70
|
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization 2024-06-13 |
코드 1 |
| RAR-L, autoregressive |
- FID
- 1.70
|
Randomized Autoregressive Visual Generation 2024-11-01 |
코드 1 |
| DiffiT |
- FID
- 1.73
|
DiffiT: Diffusion Vision Transformers for Image Generation 2023-12-04 |
코드 1 |
| VAR (Visual Autoregressive) |
- FID
- 1.73
|
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction 2024-04-03 |
코드 1 · 코드 2 · 코드 3 |
| MAGVIT-v2 |
- FID
- 1.78
|
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation 2023-10-09 |
코드 1 · 코드 2 · 코드 3 |
| MAR-L, Diff Loss |
- FID
- 1.78
|
Autoregressive Image Generation without Vector Quantization 2024-06-17 |
코드 1 · 코드 2 |
| MDT |
- FID
- 1.79
|
MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer 2023-03-25 |
코드 1 |
| Discriminator Guidance |
- FID
- 1.83
|
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models 2022-11-28 |
코드 1 · 코드 2 |
| DoD-XL |
- FID
- 1.83
|
Diffusion Models Need Visual Priors for Image Generation 2024-10-11 |
연결 없음 |
| RobustTok-B |
- FID
- 1.83
|
Robust Latent Matters: Boosting Image Generation with Sampling Error 2025-03-11 |
코드 1 |
| ARPG-XXL |
- FID
- 1.94
|
Autoregressive Image Generation with Randomized Parallel Decoding 2025-03-13 |
코드 1 |
| RAR-B, autoregressive |
- FID
- 1.95
|
Randomized Autoregressive Visual Generation 2024-11-01 |
코드 1 |
| TiTok-S-128 |
- FID
- 1.97
|
An Image is Worth 32 Tokens for Reconstruction and Generation 2024-06-11 |
코드 1 · 코드 2 |
| PixelFlow |
- FID
- 1.98
|
PixelFlow: Pixel-Space Generative Models with Flow 2025-04-10 |
코드 1 |
| RDM |
- FID
- 1.99
|
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis 2023-09-04 |
코드 1 |
| FasterDiT-XL/2 |
- FID
- 2.03
|
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification 2024-10-14 |
코드 1 |
| LEGO-XL |
- FID
- 2.05
- Inception score
- 338.08
|
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling 2023-10-10 |
코드 1 |
| ARPG-XL |
- FID
- 2.1
|
Autoregressive Image Generation with Randomized Parallel Decoding 2025-03-13 |
코드 1 |
| StyleSAN-XL |
- FID
- 2.14
|
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer 2023-01-30 |
코드 1 |
| LlamaGen |
- FID
- 2.18
|
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation 2024-06-10 |
코드 1 · 코드 2 |
| DiT-XL/2 |
- FID
- 2.27
|
Scalable Diffusion Models with Transformers 2022-12-19 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 |
| StyleGAN-XL |
- FID
- 2.30
|
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets 2022-02-01 |
코드 1 · 코드 2 |
| MAR-B, Diff Loss |
- FID
- 2.31
|
Autoregressive Image Generation without Vector Quantization 2024-06-17 |
코드 1 · 코드 2 |
| Open-MAGVIT2-XL |
- FID
- 2.33
|
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation 2024-09-06 |
코드 1 · 코드 2 |
| ACDiT |
- FID
- 2.37
|
ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer 2024-12-10 |
코드 1 |
| ARPG-L |
- FID
- 2.44
|
Autoregressive Image Generation with Randomized Parallel Decoding 2025-03-13 |
코드 1 |
| TiTok-B-64 |
- FID
- 2.48
|
An Image is Worth 32 Tokens for Reconstruction and Generation 2024-06-11 |
코드 1 · 코드 2 |